arXiv subjects

Hui Wang

Publications and source records attributed to Hui Wang.

At least 145 records · Page 8Linked to original sources

arXiv2025

PCMind-2.1-Kaiyuan-2B Technical Report

The rapid advancement of Large Language Models (LLMs) has resulted in a significant knowledge gap between the open-source community and industry, primarily because the latter relies on closed-source, high-quality data and training recipes. To address this, we introduce PCMind-2.1-Kaiyuan-2B, a fully open-source 2-billion-parameter model focused on improving training efficiency and effectiveness under resource constraints. Our methodology includes three key innovations: a Quantile Data Benchmarking method for systematically comparing heterogeneous open-source datasets and providing insights on data mixing strategies; a Strategic Selective Repetition scheme within a multi-phase paradigm to effectively leverage sparse, high-quality data; and a Multi-Domain Curriculum Training policy that orders samples by quality. Supported by a highly optimized data preprocessing pipeline and architectural modifications for FP16 stability, Kaiyuan-2B achieves performance competitive with state-of-the-art fully open-source models, demonstrating practical and scalable solutions for resource-limited pretraining. We release all assets (including model weights, data, and code) under Apache 2.0 license at https://huggingface.co/thu-pacman/PCMind-2.1-Kaiyuan-2B.

cs.CL↗

arXiv2025

AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees

The quadratic complexity of self-attention constrains Large Language Models (LLMs) in processing long contexts, a capability essential for many advanced applications. Context compression aims to alleviate this computational bottleneck while retaining critical semantic information. However, existing approaches often fall short: explicit methods may compromise local detail, whereas implicit methods can suffer from positional biases, information degradation, or an inability to capture long-range semantic dependencies. We propose AdmTree, a novel framework for adaptive, hierarchical context compression with a central focus on preserving high semantic fidelity while maintaining efficiency. AdmTree dynamically segments input based on information density, utilizing gist tokens to summarize variable-length segments as the leaves of a semantic binary tree. This structure, together with a lightweight aggregation mechanism and a frozen backbone LLM (thereby minimizing new trainable parameters), enables efficient hierarchical abstraction of the context. By preserving fine-grained details alongside global semantic coherence, mitigating positional bias, and dynamically adapting to content, AdmTree robustly retains the semantic information of long contexts.

cs.CL↗

arXiv2025

On an unconditional $\rm GL_3$ analog of Selberg's result

Let $F$ be a Hecke--Maass cusp form for $\mathrm{SL}_3(\mathbb{Z})$ with the Langlands parameter $μ_{F}=\big(μ_{F,1},μ_{F,2},μ_{F,3}\big)$ and the associated $L$-function $L(s, F)$. Define $S_F(t)=π^{-1}\arg L(1/2+\mathrm{i}t, F)$. When $μ_{F}$ is in generic position, we establish an unconditional asymptotic formula for the moments of $S_F(t)$. Previously, such a formula was only known to hold under the Generalized Riemann Hypothesis. The key ingredient is a weighted zero-density estimate in the spectral aspect for $L(s, F)$, which has recently been proved by Sun and Wang in arXiv:2412.02416.

math.NT↗

arXiv2025

FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions

We conduct a moderate-scale contamination-free (to some extent) evaluation of current large reasoning models (LRMs) with some preliminary findings. We also release ROME, our evaluation benchmark for vision language models intended to test reasoning from visual clues. We attach links to the benchmark, evaluation data, and other updates on this website: https://flageval-baai.github.io/LRM-Eval/

cs.CL↗

arXiv2025

A survey of using EHR as real-world evidence for discovering and validating new drug indications

Electronic Health Records (EHRs) have been increasingly used as real-world evidence (RWE) to support the discovery and validation of new drug indications. This paper surveys current approaches to EHR-based drug repurposing, covering data sources, processing methodologies, and representation techniques. It discusses study designs and statistical frameworks for evaluating drug efficacy. Key challenges in validation are discussed, with emphasis on the role of large language models (LLMs) and target trial emulation. By synthesizing recent developments and methodological advances, this work provides a foundational resource for researchers aiming to translate real-world data into actionable drug-repurposing evidence.

stat.AP↗

arXiv2025

Wide-Field X-ray Polarimetry for High Energy Astronomical Transients: First results of the pathfinder CXPD Cubesat Mission

The Low Energy Polarization Detector (LPD) is a key component of the next-generation large-scale Gamma-Ray Burst polarimeter, POLAR-2. It is designed for polarization observations of transient sources in the soft X-ray energy range with a wide field of view (FOV). To validate the key technologies required for wide-FOV X-ray polarization measurements, the Cosmic X-ray Polarization Detector (CXPD) CubeSat was developed as a prototype for the LPD. The CXPD is equipped with two Gas Microchannel Plate Pixel Detectors (GMPDs) that measure X-ray polarization via the photoelectric effect, where ejected photoelectrons produce ionization tracks in the gas which are imaged to reconstruct their emission directions. Laboratory calibrations of the modulation factor and energy spectra were successfully performed using linear polarized X-ray sources at 2.98 keV, 4.51 keV, 6.40 keV, and 8.05 keV. Since its launch in June 2023, the CXPD has successfully completed critical in-orbit technology verification. It has also performed polarization observations of two bright X-ray sources Sco X-1 and the transient Swift J1727.8-1613 yielding constraints on their polarization degrees and angles. Notably, this was the first time that an anti-coincidence detector had been implemented in an X-ray polarimeter, enabling in-orbit verification of the charged-particle background rejection algorithm. These results demonstrate the feasibility of wide-field soft X-ray polarization measurements and provide essential guidance for the development of the LPD for the POLAR-2 mission, thereby advancing the frontier of X-ray polarization astronomy.

astro-ph.IM↗

arXiv2025

A General Highly Accurate Online Planning Method Integrating Large Language Models into Nested Rollout Policy Adaptation for Dialogue Tasks

In goal-oriented dialogue tasks, the main challenge is to steer the interaction towards a given goal within a limited number of turns. Existing approaches either rely on elaborate prompt engineering, whose effectiveness is heavily dependent on human experience, or integrate policy networks and pre-trained policy models, which are usually difficult to adapt to new dialogue scenarios and costly to train. Therefore, in this paper, we present Nested Rollout Policy Adaptation for Goal-oriented Dialogue (NRPA-GD), a novel dialogue policy planning method that completely avoids specific model training by utilizing a Large Language Model (LLM) to simulate behaviors of user and system at the same time. Specifically, NRPA-GD constructs a complete evaluation mechanism for dialogue trajectories and employs an optimization framework of nested Monte Carlo simulation and policy self-adaptation to dynamically adjust policies during the dialogue process. The experimental results on four typical goal-oriented dialogue datasets show that NRPA-GD outperforms both existing prompt engineering and specifically pre-trained model-based methods. Impressively, NRPA-GD surpasses ChatGPT and pre-trained policy models with only a 0.6-billion-parameter LLM. The proposed approach further demonstrates the advantages and novelty of employing planning methods on LLMs to solve practical planning tasks.

cs.CL↗

arXiv2025

Out-of-Plane Nonlinear Orbital Hall Torque

Despite recent advances in orbitronics, generating out-of-plane orbital torques essential for field-free deterministic switching of perpendicular magnetization remains a key challenge. Here, we propose a strategy to produce such unconventional torques across broad classes of materials, by leveraging the nonlinear orbital Hall effect. We demonstrate that this nonlinear orbital response is dramatically amplified by topological band degeneracies, where it overwhelmingly dominates the spin response even in systems with strong spin-orbit coupling. These features are confirmed via a quantitative investigation of representative topological metals RhSi, YPtBi, and PbTaSe$_2$, by combining our theory with first-principles calculations. The resulting orbital torques substantially surpass those from linear mechanisms reported thus far. These findings propel the research of orbital transport into the nonlinear regime, broaden the scope of orbital source materials, and establish a new pathway towards high-performance orbitronic devices.

cond-mat.mtrl-sci↗

arXiv2025

SeniorTalk: A Chinese Conversation Dataset with Rich Annotations for Super-Aged Seniors

While voice technologies increasingly serve aging populations, current systems exhibit significant performance gaps due to inadequate training data capturing elderly-specific vocal characteristics like presbyphonia and dialectal variations. The limited data available on super-aged individuals in existing elderly speech datasets, coupled with overly simple recording styles and annotation dimensions, exacerbates this issue. To address the critical scarcity of speech data from individuals aged 75 and above, we introduce SeniorTalk, a carefully annotated Chinese spoken dialogue dataset. This dataset contains 55.53 hours of speech from 101 natural conversations involving 202 participants, ensuring a strategic balance across gender, region, and age. Through detailed annotation across multiple dimensions, it can support a wide range of speech tasks. We perform extensive experiments on speaker verification, speaker diarization, speech recognition, and speech editing tasks, offering crucial insights for the development of speech technologies targeting this age group.

cs.CL↗

arXiv2025

Unconditional quantum teleportational advantage of single photons

Photon loss is the biggest enemy in quantum communications. Direct transmission typically results in a small fraction of photons surviving over long distances, hindering advanced applications such as loophole-free Bell tests and device-independent quantum key distribution. Quantum teleportation offers a "disembodied" way of transferring particles through a virtual channel--quantum entanglement--which, in principle, could overcome the photon transmission loss. Experimentally, however, no previous quantum teleportation of single photons has shown a higher survival probability than using direct transmission. To overcome this challenge, here we first propose and demonstrate an all-optical scheme for remote preparation of entangled photons. Through an effective 15-dB channel loss, we realize a heralding efficiency of 82% for event-ready entangled photons. Based on the prior distributed entanglement, we demonstrate that teleportation-based transmission efficiency offers a 2.95-fold enhancement, compared to using direct transmission through the same channel, therefore establishing an unconditional teleportational advantage.

quant-ph↗

arXiv2025

JW-Flare: Accurate Solar Flare Forecasting Method Based on Multimodal Large Language Models

Solar flares, the most powerful explosive phenomena in the solar system, may pose significant hazards to spaceborne satellites and ground-based infrastructure. Despite decades of intensive research, reliable flare prediction remains a challenging task. Large Language Models, as a milestone in artificial intelligence, exhibit exceptional general knowledge and next-token prediction capabilities. Here we introduce JW-Flare, the first Multimodal Large Language Models (MLLMs) explicitly trained for solar flare forecasting through fine-tuning on textual physic parameters of solar active regions and magnetic field images. This method demonstrates state-of-the-art (SOTA) performance for large flares prediction on the test dataset. It effectively identifies all 79 X-class flares from 18,949 test samples, yielding a True Skill Statistic (TSS) of 0.95 and a True Positive Rate (TPR) of 1.00, outperforming traditional predictive models. We further investigate the capability origins of JW-Flare through explainability experiments, revealing that solar physics knowledge acquired during pre-training contributes to flare forecasting performance. Additionally, we evaluate models of different parameter scales, confirming the Scaling_Law of Large Language Models in domain-specific applications, such as solar physics. This study marks a substantial advance in both the scale and accuracy of solar flare forecasting and opens a promising avenue for AI-driven methodologies in broader scientific domains.

astro-ph.SR↗

arXiv2025

MA-GTS: A Multi-Agent Framework for Solving Complex Graph Problems in Real-World Applications

Graph-theoretic problems arise in real-world applications like logistics, communication networks, and traffic optimization. These problems are often complex, noisy, and irregular, posing challenges for traditional algorithms. Large language models (LLMs) offer potential solutions but face challenges, including limited accuracy and input length constraints. To address these challenges, we propose MA-GTS (Multi-Agent Graph Theory Solver), a multi-agent framework that decomposes these complex problems through agent collaboration. MA-GTS maps the implicitly expressed text-based graph data into clear, structured graph representations and dynamically selects the most suitable algorithm based on problem constraints and graph structure scale. This approach ensures that the solution process remains efficient and the resulting reasoning path is interpretable. We validate MA-GTS using the G-REAL dataset, a real-world-inspired graph theory dataset we created. Experimental results show that MA-GTS outperforms state-of-the-art approaches in terms of efficiency, accuracy, and scalability, with strong results across multiple benchmarks (G-REAL 94.2%, GraCoRe 96.9%, NLGraph 98.4%).MA-GTS is open-sourced at https://github.com/ZIKEYUAN/MA-GTS.git.

cs.MA↗

arXiv2025

Shape-invariant Potentials and Singular Spaces

In this work, we present two brane-world-type solutions in a two-dimensional (2D) dilaton gravity model with singular space-time backgrounds. By employing a first-order superpotential formalism, we first construct the 2D analogues of the thick brane solution previously given by Gremm and analyze the corresponding linear scalar perturbations. We show that for a model with canonical scalar matter fields, the effective potential of the linear perturbation equation is a singular Pöschl--Teller~II type, which does not admit bound states. However, for a model with non-canonical scalar fields, the effective potential becomes an exactly solvable Pöschl--Teller~I potential, which has an infinite tower of normalizable bound states. We also present a second analytic solution inspired by the work of Girardello \emph{et al.}, but with non-canonical scalar field. In this case, the linear perturbation equation is a Schrödinger equation with the Eckart potential, which is also exactly solvable.

hep-th↗

arXiv2025

DIFFA: Large Language Diffusion Models Can Listen and Understand

Recent advances in large language models (LLMs) have shown remarkable capabilities across textual and multimodal domains. In parallel, diffusion-based language models have emerged as a promising alternative to the autoregressive paradigm, offering improved controllability, bidirectional context modeling, and robust generation. However, their application to the audio modality remains underexplored. In this work, we introduce \textbf{DIFFA}, the first diffusion-based large audio-language model designed to perform spoken language understanding. DIFFA integrates a frozen diffusion language model with a lightweight dual-adapter architecture that bridges speech understanding and natural language reasoning. We employ a two-stage training pipeline: first, aligning semantic representations via an ASR objective; then, learning instruction-following abilities through synthetic audio-caption pairs automatically generated by prompting LLMs. Despite being trained on only 960 hours of ASR and 127 hours of synthetic instruction data, DIFFA demonstrates competitive performance on major benchmarks, including MMSU, MMAU, and VoiceBench, outperforming several autoregressive open-source baselines. Our results reveal the potential of diffusion-based language models for efficient and scalable audio understanding, opening a new direction for speech-driven AI. Our code will be available at https://github.com/NKU-HLT/DIFFA.git.

cs.SD↗

arXiv2025

ISAAC: Intelligent, Scalable, Agile, and Accelerated CPU Verification via LLM-aided FPGA Parallelism

Functional verification is a critical bottleneck in integrated circuit development, with CPU verification being especially time-intensive and labour-consuming. Industrial practice relies on differential testing for CPU verification, yet faces bottlenecks at nearly each stage of the framework pipeline: front-end stimulus generation lacks micro-architectural awareness, yielding low-quality and redundant tests that impede coverage closure and miss corner cases. Meanwhile, back-end simulation infrastructure, even with FPGA acceleration, often stalls on long-running tests and offers limited visibility, delaying feedback and prolonging the debugging cycle. Here, we present ISAAC, a full-stack, Large Language Model (LLM)-aided CPU verification framework with FPGA parallelism, from bug categorisation and stimulus generation to simulation infrastructure. To do so, we presented a multi-agent stimulus engine in ISAAC's front-end, infused with micro-architectural knowledge and historical bug patterns, generating highly targeted tests that rapidly achieve coverage goals and capture elusive corner cases. In ISAAC's back-end, we introduce a lightweight forward-snapshot mechanism and a decoupled co-simulation architecture between the Instruction Set Simulator (ISS) and the Design Under Test (DUT), enabling a single ISS to drive multiple DUTs in parallel. By eliminating long-tail test bottlenecks and exploiting FPGA parallelism, the simulation throughput is significantly improved. As a demonstration, we used ISAAC to verify a mature CPU that has undergone multiple successful tape-outs. Results show up to 17,536x speed-up over software RTL simulation, while detecting several previously unknown bugs, two of which are reported in this paper.

cs.AR↗

arXiv2025

LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence

We argue that progress toward general intelligence requires complementary foundation models grounded in language, the physical world, and structured data. This report presents LimiX-16M and LimiX-2M, two instantiations of our large structured-data models (LDMs). Both models treat structured data as a joint distribution over variables and missingness, thus capable of addressing a wide range of tabular tasks through query-based conditional prediction via a single model. They are pretrained using masked joint-distribution modeling with an episodic, context-conditional objective, supporting rapid, training-free adaptation at inference. We evaluate LimiX models across 11 large structured-data benchmarks with broad regimes of sample size, feature dimensionality, class number, categorical-to-numerical feature ratio, missingness, and sample-to-feature ratios. LimiX-16M consistently surpasses strong baselines, as shown in Figure 1 and Figure 2. The superiority holds across a wide range of tasks, such as classification, regression, missing value imputation, and data generation, often by substantial margins, while avoiding task-specific architectures or bespoke training per task. Notably, LimiX-2M delivers strong results under tight compute and memory budgets. We also present the first scaling law study for LDMs, revealing how data and model scaling jointly influence downstream performance and offering quantitative guidance for tabular foundation modeling. All LimiX models are publicly accessible under Apache 2.0.

cs.LG↗

arXiv2025

Lorentz Skew Scattering Nonreciprocal Magneto-Transport

In materials with broken inversion symmetry, nonreciprocal magneto-transport (NRMT) manifests as a bilinear dependence of charge conductivity on applied electric (E) and magnetic (B) fields. This phenomenon is deeply rooted in symmetry and electronic quantum geometry, holding promise for novel rectification and detector technologies. Existing experimental studies generally attribute NRMT to Zeeman-driven mechanisms and exhibit quadratic scaling with conductivity. Here, we report a previously unknown NRMT microscopic mechanism - Lorentz skew scattering (LSK) - revealed through the discovery of an unprecedented quartic scaling law of NRMT as well as quantitative agreement between theory and experiment in BiTeBr. LSK emerges from the interplay of Lorentz force and skew scattering, bridging classical field effect to quantum scattering effect on the Fermi surface. We demonstrate that the LSK dominates NRMT in BiTeBr, and elucidate that this dominance over other possible contributions stems from high mobility and strong Rashba splitting. The finding of LSK mechanism is of unique importance because it unveils the leading NRMT effect in high-mobility systems and suggests a universal principle towards strong NRMT by enhancing electronic relaxation time in topological materials, rendering a new designing idea for low-dissipation rectifiers and high-performance quantum electronics.

cond-mat.mes-hall↗

arXiv2025

Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning

Efficient instruction tuning aims to enhance the ultimate performance of large language models (LLMs) trained on a given instruction dataset. Curriculum learning as a typical data organization strategy has shown preliminary effectiveness in instruction tuning. However, current curriculum tuning methods suffer from the curriculum rigidity, since they rely solely on static heuristic difficulty metrics. These methods fail to adapt to the evolving capabilities of models during training, resulting in a fixed and potentially sub-optimal learning trajectory. To address the issue, Competence-Aware Multi-Perspective cUrriculum inStruction tuning framework termed CAMPUS is proposed. CAMPUS offers several advantages: (1) Dynamic selection for sub-curriculum. (2) Competency-aware adjustment to the curriculum schedule. (3) Multiple difficulty-based scheduling. Extensive experiments prove the superior performance of CAMPUS, compared to other state-of-the-art baselines for efficient instruction tuning.

cs.CL↗