arXiv subjects

Shulin Liu

Publications and source records attributed to Shulin Liu.

11 recordsLinked to original sources

arXiv2026

Diffusion Attention Expert Model for Predicting and Semi-automatic Localizing STAS in Lung Cancer Histopathological Images

Accurate intraoperative and postoperative diagnosis of spread through air spaces (STAS) is essential for guiding surgical decisions and postoperative management in lung cancer. However, histopathological assessment is labor-intensive and is prone to missed or incorrect diagnoses. We propose a Diffusion Attention Expert Model (DAEM) to detect STAS in frozen sections (FSs) and paraffin sections (PSs). Its diffusion attention expert module leverages full attention aggregation to learn multi-scale features from histopathological images, while a dual-branch architecture strengthens multi-scale feature representation. On an internal dataset, DAEM achieves AUCs of 0.8946 for FSs and 0.9112 for PSs. Validation on external multi-center datasets from eight institutions demonstrates strong generalizability and interpretability. Using tumor microenvironment (TME) features in PSs, we further enable semi-automatic measurement of STAS location and its distance from the primary tumor. Several quantitative TME metrics are identified as potential biomarkers for STAS, including micropapillary-type STAS. Overall, DAEM offers a clinically actionable framework for STAS assessment by enabling accurate and interpretable detection on FSs and PSs, supporting postoperative risk stratification through quantitative TME-based analysis.

cs.CV↗

arXiv2025

MarsRL: Advancing Multi-Agent Reasoning System via Reinforcement Learning with Agentic Pipeline Parallelism

Recent progress in large language models (LLMs) has been propelled by reinforcement learning with verifiable rewards (RLVR) and test-time scaling. However, the limited output length of LLMs constrains the depth of reasoning attainable in a single inference process. Multi-agent reasoning systems offer a promising alternative by employing multiple agents including Solver, Verifier, and Corrector, to iteratively refine solutions. While effective in closed-source models like Gemini 2.5 Pro, they struggle to generalize to open-source models due to insufficient critic and correction capabilities. To address this, we propose MarsRL, a novel reinforcement learning framework with agentic pipeline parallelism, designed to jointly optimize all agents in the system. MarsRL introduces agent-specific reward mechanisms to mitigate reward noise and employs pipeline-inspired training to enhance efficiency in handling long trajectories. Applied to Qwen3-30B-A3B-Thinking-2507, MarsRL improves AIME2025 accuracy from 86.5% to 93.3% and BeyondAIME from 64.9% to 73.8%, even surpassing Qwen3-235B-A22B-Thinking-2507. These findings highlight the potential of MarsRL to advance multi-agent reasoning systems and broaden their applicability across diverse reasoning tasks.

cs.AI↗

arXiv2025

UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities

Recent advances in large language models (LLMs) have highlighted the potential of reinforcement learning with verifiable rewards (RLVR) to enhance reasoning capabilities through extended output sequences. However, traditional RL frameworks face inefficiencies when handling ultra-long outputs due to long-tail sequence distributions and entropy collapse during training. To address these challenges, we propose an Ultra-Long Output Reinforcement Learning (UloRL) approach for advancing large language models' reasoning abilities. Specifically, we divide ultra long output decoding into short segments, enabling efficient training by mitigating delays caused by long-tail samples. Additionally, we introduce dynamic masking of well-Mastered Positive Tokens (MPTs) to prevent entropy collapse. Experimental results demonstrate the effectiveness of our approach. On the Qwen3-30B-A3B model, RL with segment rollout achieved 2.06x increase in training speed, while RL training with 128k-token outputs improves the model's performance on AIME2025 from 70.9\% to 85.1\% and on BeyondAIME from 50.7\% to 61.9\%, even surpassing Qwen3-235B-A22B with remarkable gains. These findings underscore the potential of our methods to advance the reasoning capabilities of LLMs with ultra-long sequence generation. We will release our code and model for further use by the community.

cs.CL↗

arXiv2025

First experimental proof of PET imaging based on multi-anode MCP-PMTs with Cherenkov radiator-integrated window

Improving the coincidence time resolution (CTR) of time-of-flight positron emission tomography (TOF-PET) systems to achieve a higher signal-to-noise ratio (SNR) gain or even direct positron emission imaging (dPEI) is of paramount importance for many advanced new clinical applications of PET imaging. This places higher demands on the timing performance of all aspects of PET systems. One effective approach is to use microchannel plate photomultiplier tubes (MCP-PMTs) for prompt Cherenkov photon detection. In this study, we developed a dual-module Cherenkov PET imaging experimental platform, utilising our proprietary 8 * 8-anode Cherenkov radiator-integrated window MCP-PMTs in combination with custom-designed multi-channel electronics, and designed a specific calibration and correction method for the platform. Using this platform, a CTR of 103 ps FWHM was achieved. We overcame the limitations of single-anode detectors in previous experiments, significantly enhanced imaging efficiency and achieved module-level Cherenkov PET imaging for the first time. Imaging experiments involving radioactive sources and phantoms of various shapes and types were conducted, which preliminarily validated the feasibility and advancement of this imaging method. In addition, the effects of normalisation correction and the interaction probability between the gamma rays and the MCP on the images and experimental results were analysed and verified.

physics.ins-det↗

arXiv2024

Metasurface-Integrated Polarization-Insensitive LCoS for Projection Displays

Liquid crystal on silicon (LCoS) panels, renowned for their high resolution and fill-factor, are integral to modern projection displays. However, their inherent polarization sensitivity constrains the upper limit of light utilization, increases system complexity and restricts broader applicability. Here, we demonstrate a dual-layer metasurface-integrated LCoS prototype that achieves polarization-insensitive, addressable amplitude modulation in the visible. Polarization sensitivity is eliminated in the reflective architecture through polarization conversion in the underlying metasurface and polarization-sensitive phase modulation of the liquid crystals (LC). This is further enhanced by the electrically tunable subwavelength grating formed by the upper metasurface and LC, resulting in a high-contrast, polarization-insensitive optical switch. We showcase a 64-pixel 2D addressable prototype capable of generating diverse projection patterns with high contrast. Compatible with existing LCoS processes, our metasurface device reduces system size and enhances energy efficiency, offering applications in projectors and AR/VR displays, with the potential to redefine projection chip technology.

physics.optics↗

arXiv2024

Conceptual Design of the Muonium-to-Antimuonium Conversion Experiment (MACE)

The spontaneous conversion of muonium to antimuonium is one of the interesting charged lepton flavor violation phenomena offering a sensitive probe of potential new physics and serving as a tool to constrain the parameter space beyond the Standard Model. The Muonium-to-Antimuonium Conversion Experiment (MACE) is designed to utilize a high-intensity muon beam, a Michel electron magnetic spectrometer, a positron transport system, and a positron detection system, to either discover or constrain this rare process with a conversion probability of $\mathcal{O}(10^{-13})$. This article presents an overview of the theoretical framework as well as a detailed description of the experimental design for the search for muonium-to-antimuonium conversion.

hep-ex↗

arXiv2024

Are LLMs Effective Backbones for Fine-tuning? An Experimental Investigation of Supervised LLMs on Chinese Short Text Matching

The recent success of Large Language Models (LLMs) has garnered significant attention in both academia and industry. Prior research on LLMs has primarily focused on enhancing or leveraging their generalization capabilities in zero- and few-shot settings. However, there has been limited investigation into effectively fine-tuning LLMs for a specific natural language understanding task in supervised settings. In this study, we conduct an experimental analysis by fine-tuning LLMs for the task of Chinese short text matching. We explore various factors that influence performance when fine-tuning LLMs, including task modeling methods, prompt formats, and output formats.

cs.CL↗

arXiv2023

Simulating the secondary electron avalanche of MCP by Geant4

Nowadays, Microchannel Plate (MCP), as a kind of electron multipliers based on the secondary electron emission, is widely used in many high-sensitive experiments, such as neutrino detection, which require the noise to be as low as possible, while the conventional straight-channel MCP will inevitably have ion feedback, resulting in the sequential after-pulses being the major source of noise. Normally, the problem can be effectively avoided by coupling two straight-channel MCPs in cascade and combining the channels into a `V` shape known as chevron MCPs, but this method is limited by the manufacturing techniques due to the unavoidable gap between the two pieces that will worsen the resolution and peak-to-valley ratio. However, the ion feedback can be inhibited significantly for MCPs with curved channels. Based on Geant4, we investigate how the geometrical parameters of curved-channel MCP influence the gain and get the optimum pore diameter for an MCP to reach the maximum gain with fixed thickness and applied voltage. Additionally, the track-by-track simulation reveals that the average acceleration distance of a secondary electron inside the curved-channel is approximately 20 um when the applied voltage, length-to-diameter ratio and pore diameter are 950 V, 50:1 and 20 um, respectively.

physics.ins-det↗

arXiv2023

MCPSim: A Geant4-based generic simulation toolkit for electron multipliers represented by Microchannel Plate

The simulation of the instruments based on the cascade multiplication of electrons has always been an important and challenging subject in no matter high energy physics, astrophysics, radiography and other fields. In this work, a generic simulation toolkit is developed based on Geant4, ROOT and CADMesh toolkits for the electron multipliers based on the emission process of secondary electrons, especially for Microchannel Plate (MCP). Geometry of instruments can be directly imported by standard CAD files and multiple kinds of electromagnetic fields are supported. MCPSim is capable for simulating the general hadronic, weak and electromagnetic processes together with secondary electron emission, which provides a wider range of applications. Users are able to configure the simulation and define the output information by a simple textfile. By comparing with experimental measurements, good agreement is found. MCPSim is expected to guide the design and optimization of such electron multipliers and will be continuously developed and maintained to better satisfy the present and future requirements.

physics.ins-det↗

arXiv2017

Study on the large area MCP-PMT glass radioactivity reduction

The Jiangmen Underground Neutrino Observatory (JUNO) will install about 18,000 20-inch Photomultiplier Tubes (PMTs) in the center detector to achieve 3%/sqrt(E(MeV)) energy resolution. From the full detector Monte Carlo (MC) simulation, besides the liquid scitillator (LS) and Acrylic nodes, PMT glass has the largest contribution to the natural radioactive background. Various technologies have been developed in the Chinese industry to control the environment and to improve the production process. We have monitored the glass production for more than two months, and the radioactivity in glass was measured using a low background gamma ray spectrometer equipped with a high resolution HPGe detector. The 238U, 232Th and 40K of the glass bulb are reduced by a factor of 2, 9 and 15 respectively, and now they can reach 2.5 Bq/kg for 238U, 0.5 Bq/kg for 232Th and 0.5 Bq/kg for 40K.

physics.ins-det↗

arXiv2014

The high-speed after pulse measurement system for PMT

A system employing a desktop FADC has been developed to investigate the features of 8 inches Hamamatsu PMT. The system stands out for its high-speed and informative results as a consequence of adopting fast waveform sampling technology. Recording full waveforms allows us to perform digital signal processing, pulse shape analysis, and precision timing extraction. High precision after pulse time and charge distribution characteristics are presented in this manuscript. Other photomultipliers characteristics, such as dark rate and transit time spread, can also be obtained by exploiting waveform analysis using this system.

physics.ins-det↗