arXiv subjects

Lei Wang

Publications and source records attributed to Lei Wang.

At least 397 records · Page 22Linked to original sources

arXiv2025

E2MPL:An Enduring and Efficient Meta Prompt Learning Framework for Few-shot Unsupervised Domain Adaptation

Few-shot unsupervised domain adaptation (FS-UDA) leverages a limited amount of labeled data from a source domain to enable accurate classification in an unlabeled target domain. Despite recent advancements, current approaches of FS-UDA continue to confront a major challenge: models often demonstrate instability when adapted to new FS-UDA tasks and necessitate considerable time investment. To address these challenges, we put forward a novel framework called Enduring and Efficient Meta-Prompt Learning (E2MPL) for FS-UDA. Within this framework, we utilize the pre-trained CLIP model as the backbone of feature learning. Firstly, we design domain-shared prompts, consisting of virtual tokens, which primarily capture meta-knowledge from a wide range of meta-tasks to mitigate the domain gaps. Secondly, we develop a task prompt learning network that adaptively learns task-specific specific prompts with the goal of achieving fast and stable task generalization. Thirdly, we formulate the meta-prompt learning process as a bilevel optimization problem, consisting of (outer) meta-prompt learner and (inner) task-specific classifier and domain adapter. Also, the inner objective of each meta-task has the closed-form solution, which enables efficient prompt learning and adaptation to new tasks in a single step. Extensive experimental studies demonstrate the promising performance of our framework in a domain adaptation benchmark dataset DomainNet. Compared with state-of-the-art methods, our method has improved accuracy by at least 15.4% and reduced the time by 68.5% on average in 5-way 1-shot tasks, and improved accuracy by 8.7% and reduced the time by 74.1% on average in 5-way 5-shot tasks. Moreover, our approach exhibits more enduring performance than the other methods, i.e., being more stable across 3600 test tasks.

cs.CV↗

arXiv2025

A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce

Reinforcement learning (RL) has become a prevailing approach for fine-tuning large language models (LLMs) on complex reasoning tasks. Among recent methods, GRPO stands out for its empirical success in training models such as DeepSeek-R1, yet the sources of its effectiveness remain poorly understood. In this work, we revisit GRPO from a reinforce-like algorithm perspective and analyze its core components. Surprisingly, we find that a simple rejection sampling baseline, RAFT, which trains only on positively rewarded samples, yields competitive performance than GRPO and PPO. Our ablation studies reveal that GRPO's main advantage arises from discarding prompts with entirely incorrect responses, rather than from its reward normalization. Motivated by this insight, we propose Reinforce-Rej, a minimal extension of policy gradient that filters both entirely incorrect and entirely correct samples. Reinforce-Rej improves KL efficiency and stability, serving as a lightweight yet effective alternative to more complex RL algorithms. We advocate RAFT as a robust and interpretable baseline, and suggest that future advances should focus on more principled designs for incorporating negative samples, rather than relying on them indiscriminately. Our findings provide guidance for future work in reward-based LLM post-training.

cs.LG↗

arXiv2025

Charged-current quasielastic neutrino scattering off nuclei with nucleon-nucleon short-range correlations

In recent years, many studies on neutrino-nucleus scattering have been carried out to investigate nuclear structures and the interactions between neutrinos and nucleons. This paper develops a charged-current quasielastic (CCQE) neutrino-nucleus scattering model to explore the nuclear mean-field dynamics and short-range correlation effects. In this model, the nuclear structure effect is depicted using the scaling function, while the neutrinonucleon interaction is represented by the elementary weak cross section. Results indicate that the double-differential cross section of scattered muon is influenced by the energy and momentum of nucleon in nuclei, and the total cross section depends primarily on the incident neutrino energy. Furthermore, incorporating short-range correlations yields the flux-integrated differential cross sections at high-T region producing larger values, a longer tail, and achieving better experimental consistency. It eventually elucidates the physical relationship between the neutrinonucleus scattering cross section and the variation in incident neutrino energy. The studies in this paper furnishes insights for the research of nucleon dynamics and provides detailed examinations of the neutrino-nucleus scattering mechanism.

nucl-th↗

arXiv2025

ChartReasoner: Code-Driven Modality Bridging for Long-Chain Reasoning in Chart Question Answering

Recently, large language models have shown remarkable reasoning capabilities through long-chain reasoning before responding. However, how to extend this capability to visual reasoning tasks remains an open challenge. Existing multimodal reasoning approaches transfer such visual reasoning task into textual reasoning task via several image-to-text conversions, which often lose critical structural and semantic information embedded in visualizations, especially for tasks like chart question answering that require a large amount of visual details. To bridge this gap, we propose ChartReasoner, a code-driven novel two-stage framework designed to enable precise, interpretable reasoning over charts. We first train a high-fidelity model to convert diverse chart images into structured ECharts codes, preserving both layout and data semantics as lossless as possible. Then, we design a general chart reasoning data synthesis pipeline, which leverages this pretrained transport model to automatically and scalably generate chart reasoning trajectories and utilizes a code validator to filter out low-quality samples. Finally, we train the final multimodal model using a combination of supervised fine-tuning and reinforcement learning on our synthesized chart reasoning dataset and experimental results on four public benchmarks clearly demonstrate the effectiveness of our proposed ChartReasoner. It can preserve the original details of the charts as much as possible and perform comparably with state-of-the-art open-source models while using fewer parameters, approaching the performance of proprietary systems like GPT-4o in out-of-domain settings.

cs.CL↗

arXiv2025

Visible Brillouin-quadratic microlaser in a high-Q thin-film lithium niobate microdisk

Narrow-linewidth lasers at short/visible wavelengths are crucial for quantum and atomic applications, such as atomic clocks, quantum computing, atomic and molecular spectroscopy, and quantum sensing. However, such lasers are often only accessible in bulky tabletop systems and remain scarce in integrated photonic platform. Here, we report an on-chip visible Brillouin-quadratic microlaser in a 117-um-diameter thin-film lithium niobate (TFLN) microdisk via dispersion engineering. Enabled by the ultra-high Q factor of 4.0X10(6) and small mode volume, strong photon-phonon interaction and high second-order nonlinearity of the TFLN microdisk, narrow-linewidth Stokes Brillouin lasing (SBL) is demonstrated with 10.17 GHz Brillouin shift under a 1560-nm pump, exhibiting a short-term narrow linewidth of 254 Hz and a low threshold of only 1.81 mW. Meanwhile, efficient second harmonic generation (SHG) of the SBL signal is also observed at 780 nm, with a normalized conversion efficiency of 3.61%/mW, made possible by simultaneous phase matching fulfillments for both narrow-linewidth SBL and its SHG. This demonstration of an integrated ultra-narrow linewidth visible wavelength Brillouin-quadratic lasers opens new avenues toward chip-scale quantum information processing and precise metrology.

physics.optics↗

arXiv2025

SeerAttention-R: Sparse Attention Adaptation for Long Reasoning

We introduce SeerAttention-R, a sparse attention framework specifically tailored for the long decoding of reasoning models. Extended from SeerAttention, SeerAttention-R retains the design of learning attention sparsity through a self-distilled gating mechanism, while removing query pooling to accommodate auto-regressive decoding. With a lightweight plug-in gating, SeerAttention-R is flexible and can be easily integrated into existing pretrained model without modifying the original parameters. We demonstrate that SeerAttention-R, trained on just 0.4B tokens, maintains near-lossless reasoning accuracy with 4K token budget in AIME benchmark under large sparse attention block sizes (64/128). Using TileLang, we develop a highly optimized sparse decoding kernel that achieves near-theoretical speedups of up to 9x over FlashAttention-3 on H100 GPU at 90% sparsity. Code is available at: https://github.com/microsoft/SeerAttention.

cs.LG↗

arXiv2025

Modern applications of machine learning in quantum sciences

In this book, we provide a comprehensive introduction to the most recent advances in the application of machine learning methods in quantum sciences. We cover the use of deep learning and kernel methods in supervised, unsupervised, and reinforcement learning algorithms for phase classification, representation of many-body quantum states, quantum feedback control, and quantum circuits optimization. Moreover, we introduce and discuss more specialized topics such as differentiable programming, generative models, statistical approach to machine learning, and quantum machine learning.

quant-ph↗

arXiv2025

ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering

Chart question answering (CQA) has become a critical multimodal task for evaluating the reasoning capabilities of vision-language models. While early approaches have shown promising performance by focusing on visual features or leveraging large-scale pre-training, most existing evaluations rely on rigid output formats and objective metrics, thus ignoring the complex, real-world demands of practical chart analysis. In this paper, we introduce ChartMind, a new benchmark designed for complex CQA tasks in real-world settings. ChartMind covers seven task categories, incorporates multilingual contexts, supports open-domain textual outputs, and accommodates diverse chart formats, bridging the gap between real-world applications and traditional academic benchmarks. Furthermore, we propose a context-aware yet model-agnostic framework, ChartLLM, that focuses on extracting key contextual elements, reducing noise, and enhancing the reasoning accuracy of multimodal large language models. Extensive evaluations on ChartMind and three representative public benchmarks with 14 mainstream multimodal models show our framework significantly outperforms the previous three common CQA paradigms: instruction-following, OCR-enhanced, and chain-of-thought, highlighting the importance of flexible chart understanding for real-world CQA. These findings suggest new directions for developing more robust chart reasoning in future research.

cs.CL↗

arXiv2025

Enhanced Light Extraction and Beam Focusing in GaN LEDs Using Hybrid Metasurface-Distributed Bragg Reflector Structures

This study presents an optimized hybrid design integrating a distributed Bragg reflector (DBR) and a TiO2 nanocylinder metasurface to enhance light extraction efficiency (LEE) and beam directionality(narrow divergence angle) in light-emitting diodes (LEDs) based on gallium nitride (GaN).Parametric simulations were used to identify an optimal device architecture.The resulting structure comprises a single-period DBR,which has a thickness of TiO2(dTiO2) equal to forty-six nm and a thickness of SiO2 equal to seventy-sevsen nm,beneath a periodic array of TiO2 nanocylinders (radius is approximately seventy-one nm,height is approximately one handred and eighty-five nm).The DBR reflects guided modes to minimize internal optical losses,while the TiO2 metasurface employs Mie resonance to collimate the emitted light.As a result,the hybrid LED achieves a simulated LEE of 25.67 percent and a beam divergence angle of only 5.7 degree,representing a significant improvement in both efficiency and emission directionality over conventional designs.These findings demonstrate a viable strategy to overcome light trapping and broad angular emission in GaN LEDs,paving the way for high-brightness,highly directional GaN micro-LEDs for advanced display and optical communication applications.

physics.optics↗

arXiv2025

Dominant Kitaev interaction and field-induced quantum phase transitions in triangular-lattice KCeSe2

Realizing Kitaev interactions on triangular lattices offers a compelling platform for exploring quantum-spin-liquid physics beyond the conventional honeycomb lattice framework. Here, we investigate the triangular-lattice antiferromagnet KCeSe2, where multiple probes reveal strong magnetic anisotropy suggesting significant Kitaev physics. Through detailed and combined analysis of magnetization, neutron scattering, and thermodynamic experiments, we identify dominant ferromagnetic Kitaev ($K = -1.82$ K) and antiferromagnetic Heisenberg ($J = 1.34$ K) interactions that stabilize a stripe-$yz$ ordered ground state via an order-by-disorder mechanism. Magnetic fields applied along the Kitaev bond direction induce two phase transitions at 1.67 T and 3.8 T, consistent with density matrix renormalization group (DMRG) calculations predictions of a progression from stripe-$yz$ to stripe-canted and spin-polarized phases. Near the 1.67 T quantum critical point, enhanced quantum fluctuations suggest conditions favorable for exotic excitations. These results establish KCeSe2 as a platform for exploring Kitaev physics on triangular lattices.

cond-mat.str-el↗

arXiv2025

One-Way Ticket:Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models

Text-to-Image (T2I) diffusion models have made remarkable advancements in generative modeling; however, they face a trade-off between inference speed and image quality, posing challenges for efficient deployment. Existing distilled T2I models can generate high-fidelity images with fewer sampling steps, but often struggle with diversity and quality, especially in one-step models. From our analysis, we observe redundant computations in the UNet encoders. Our findings suggest that, for T2I diffusion models, decoders are more adept at capturing richer and more explicit semantic information, while encoders can be effectively shared across decoders from diverse time steps. Based on these observations, we introduce the first Time-independent Unified Encoder TiUE for the student model UNet architecture, which is a loop-free image generation approach for distilling T2I diffusion models. Using a one-pass scheme, TiUE shares encoder features across multiple decoder time steps, enabling parallel sampling and significantly reducing inference time complexity. In addition, we incorporate a KL divergence term to regularize noise prediction, which enhances the perceptual realism and diversity of the generated images. Experimental results demonstrate that TiUE outperforms state-of-the-art methods, including LCM, SD-Turbo, and SwiftBrushv2, producing more diverse and realistic results while maintaining the computational efficiency.

cs.CV↗

arXiv2025

Multimodal Federated Learning: A Survey through the Lens of Different FL Paradigms

Multimodal Federated Learning (MFL) lies at the intersection of two pivotal research areas: leveraging complementary information from multiple modalities to improve downstream inference performance and enabling distributed training to enhance efficiency and preserve privacy. Despite the growing interest in MFL, there is currently no comprehensive taxonomy that organizes MFL through the lens of different Federated Learning (FL) paradigms. This perspective is important because multimodal data introduces distinct challenges across various FL settings. These challenges, including modality heterogeneity, privacy heterogeneity, and communication inefficiency, are fundamentally different from those encountered in traditional unimodal or non-FL scenarios. In this paper, we systematically examine MFL within the context of three major FL paradigms: horizontal FL (HFL), vertical FL (VFL), and hybrid FL. For each paradigm, we present the problem formulation, review representative training algorithms, and highlight the most prominent challenge introduced by multimodal data in distributed settings. We also discuss open challenges and provide insights for future research. By establishing this taxonomy, we aim to uncover the novel challenges posed by multimodal data from the perspective of different FL paradigms and to offer a new lens through which to understand and advance the development of MFL.

cs.LG↗

arXiv2025

Neural Canonical Transformations for Quantum Anharmonic Solids of Lithium

Lithium is a typical quantum solid, characterized by cubic structures at ambient pressure. As the pressure increases, it forms more complex structures and undergoes a metal-to-semiconductor transformation, complicating theoretical and experimental analyses. We employ the neural canonical transformation approach, an \textit{ab initio} variational method based on probabilistic generative models, to investigate the quantum anharmonic effects in lithium solids at finite temperatures. This approach combines a normalizing flow for phonon excited-state wave functions with a probabilistic model for the occupation of energy levels, optimized jointly to minimize the free energy. Our results indicate that quantum anharmonicity lowers the \textit{bcc}-\textit{fcc} transition temperature compared to classical molecular dynamics predictions. At high pressures, the predicted fractional coordinates of lithium atoms in the \textit{cI16} structure show good quantitative agreement with experimental observations. Finally, contrary to previous beliefs, we find that the poor metallic \textit{oC88} structure is stabilized by the potential energy surface obtained via high-accuracy electronic structure calculations, rather than thermal or quantum nuclear effects.

cond-mat.mtrl-sci↗

arXiv2025

Ontology- and LLM-based Data Harmonization for Federated Learning in Healthcare

The rise of electronic health records (EHRs) has unlocked new opportunities for medical research, but privacy regulations and data heterogeneity remain key barriers to large-scale machine learning. Federated learning (FL) enables collaborative modeling without sharing raw data, yet faces challenges in harmonizing diverse clinical datasets. This paper presents a two-step data alignment strategy integrating ontologies and large language models (LLMs) to support secure, privacy-preserving FL in healthcare, demonstrating its effectiveness in a real-world project involving semantic mapping of EHR data.

cs.LG↗

arXiv2025

Quantum melting of generalized electron crystal in twisted bilayer MoSe2

Electrons can form an ordered solid crystal phase ascribed to the interplay between Coulomb repulsion and kinetic energy. Tuning these energy scales can drive a phase transition from electron solid to liquid, i.e. melting of Wigner crystal. Generalized Wigner crystals (GWCs) pinned to moire superlattices have been reported by optical and scanning-probe-based methods. Using transport measurements to investigate GWCs is vital to a complete characterization, however, still poses a significant challenge due to difficulties in making reliable electrical contacts. Here, we report the electrical transport detection of GWCs at fractional fillings nu = 2/5, 1/2, 3/5, 2/3, 8/9, 10/9, and 4/3 in twisted bilayer MoSe2. We further observe that these GWCs undergo continuous quantum melting transitions to liquid phases by tuning doping density, magnetic and displacement fields, manifested by quantum critical scaling behaviors. Our findings establish twisted bilayer MoSe2 as a novel system to study strongly correlated states of matter and their quantum phase transitions.

cond-mat.str-el↗

arXiv2025

Detecting Fake News Belief via Skin and Blood Flow Signals

Misinformation poses significant risks to public opinion, health, and security. While most fake news detection methods rely on text analysis, little is known about how people physically respond to false information or repeated exposure to the same statements. This study investigates whether wearable sensors can detect belief in a statement or prior exposure to it. We conducted a controlled experiment where participants evaluated statements while wearing an EmotiBit sensor that measured their skin conductance (electrodermal activity, EDA) and peripheral blood flow (photoplethysmography, PPG). From 28 participants, we collected a dataset of 672 trials, each labeled with whether the participant believed the statement and whether they had seen it before. This dataset introduces a new resource for studying physiological responses to misinformation. Using machine learning models, including KNN, CNN, and LightGBM, we analyzed these physiological patterns. The best-performing model achieved 67.83\% accuracy, with skin conductance outperforming PPG. These findings demonstrate the potential of wearable sensors as a minimally intrusive tool for detecting belief and prior exposure, offering new directions for real-time misinformation detection and adaptive, user-aware systems.

cs.HC↗

arXiv2025

Truth and Trust: Fake News Detection via Biosignals

Understanding how individuals physiologically respond to false information is crucial for advancing misinformation detection systems. This study explores the potential of using physiological signals, specifically electrodermal activity (EDA) and photoplethysmography (PPG), to classify both the veracity of information and its interaction with user belief. In a controlled laboratory experiment, we collected EDA and PPG signals while participants evaluated the truthfulness of climate-related claims. Each trial was labeled based on the objective truth of the claim and the participant's belief, enabling two classification tasks: binary veracity detection and a novel four-class joint belief-veracity classification. We extracted handcrafted features from the raw signals and trained several machine learning models to benchmark the dataset. Our results show that EDA outperforms PPG, indicating its greater sensitivity to physiological responses related to truth perception. However, performance significantly drops in the joint belief-veracity classification task, highlighting the complexity of modeling the interaction between belief and truth. These findings suggest that while physiological signals can reflect basic truth perception, accurately modeling the intricate relationships between belief and veracity remains a significant challenge. This study emphasizes the importance of multimodal approaches that incorporate psychological, physiological, and cognitive factors to improve fake news detection systems. Our work provides a foundation for future research aimed at enhancing misinformation detection via addressing the complexities of human belief and truth processing.

cs.HC↗

arXiv2025

Scalable Chain of Thoughts via Elastic Reasoning

Large reasoning models (LRMs) have achieved remarkable progress on complex tasks by generating extended chains of thought (CoT). However, their uncontrolled output lengths pose significant challenges for real-world deployment, where inference-time budgets on tokens, latency, or compute are strictly constrained. We propose Elastic Reasoning, a novel framework for scalable chain of thoughts that explicitly separates reasoning into two phases--thinking and solution--with independently allocated budgets. At test time, Elastic Reasoning prioritizes the completeness of solution segments, significantly improving reliability under tight resource constraints. To train models that are robust to truncated thinking, we introduce a lightweight budget-constrained rollout strategy, integrated into GRPO, which teaches the model to reason adaptively when the thinking process is cut short and generalizes effectively to unseen budget constraints without additional training. Empirical results on mathematical (AIME, MATH500) and programming (LiveCodeBench, Codeforces) benchmarks demonstrate that Elastic Reasoning performs robustly under strict budget constraints, while incurring significantly lower training cost than baseline methods. Remarkably, our approach also produces more concise and efficient reasoning even in unconstrained settings. Our code has been made available at https://github.com/SalesforceAIResearch/Elastic-Reasoning.

cs.LG↗