arXiv subjects

Shuang Zhou

Publications and source records attributed to Shuang Zhou.

At least 37 records · Page 2Linked to original sources

arXiv2026

To Reason or Not to: Selective Chain-of-Thought in Medical Question Answering

Objective: To improve the efficiency of medical question answering (MedQA) with large language models (LLMs) by avoiding unnecessary reasoning while maintaining accuracy. Methods: We propose Selective Chain-of-Thought (Selective CoT), an inference-time strategy that first predicts whether a question requires reasoning and generates a rationale only when needed. Two open-source LLMs (Llama-3.1-8B and Qwen-2.5-7B) were evaluated on four biomedical QA benchmarks-HeadQA, MedQA-USMLE, MedMCQA, and PubMedQA. Metrics included accuracy, total generated tokens, and inference time. Results: Selective CoT reduced inference time by 13-45% and token usage by 8-47% with minimal accuracy loss ($\leq$4\%). In some model-task pairs, it achieved both higher accuracy and greater efficiency than standard CoT. Compared with fixed-length CoT, Selective CoT reached similar or superior accuracy at substantially lower computational cost. Discussion: Selective CoT dynamically balances reasoning depth and efficiency by invoking explicit reasoning only when beneficial, reducing redundancy on recall-type questions while preserving interpretability. Conclusion: Selective CoT provides a simple, model-agnostic, and cost-effective approach for medical QA, aligning reasoning effort with question complexity to enhance real-world deployability of LLM-based clinical systems.

cs.CL↗

arXiv2026

LongCat-Flash-Thinking-2601 Technical Report

We introduce LongCat-Flash-Thinking-2601, a 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model with superior agentic reasoning capability. LongCat-Flash-Thinking-2601 achieves state-of-the-art performance among open-source models on a wide range of agentic benchmarks, including agentic search, agentic tool use, and tool-integrated reasoning. Beyond benchmark performance, the model demonstrates strong generalization to complex tool interactions and robust behavior under noisy real-world environments. Its advanced capability stems from a unified training framework that combines domain-parallel expert training with subsequent fusion, together with an end-to-end co-design of data construction, environments, algorithms, and infrastructure spanning from pre-training to post-training. In particular, the model's strong generalization capability in complex tool-use are driven by our in-depth exploration of environment scaling and principled task construction. To optimize long-tailed, skewed generation and multi-turn agentic interactions, and to enable stable training across over 10,000 environments spanning more than 20 domains, we systematically extend our asynchronous reinforcement learning framework, DORA, for stable and efficient large-scale multi-environment training. Furthermore, recognizing that real-world tasks are inherently noisy, we conduct a systematic analysis and decomposition of real-world noise patterns, and design targeted training procedures to explicitly incorporate such imperfections into the training process, resulting in improved robustness for real-world applications. To further enhance performance on complex reasoning tasks, we introduce a Heavy Thinking mode that enables effective test-time scaling by jointly expanding reasoning depth and width through intensive parallel thinking.

cs.AI↗

arXiv2026

Balanced Edge Pruning for Graph Anomaly Detection with Noisy Labels

Graph anomaly detection (GAD) is widely applied in many areas, such as financial fraud detection and social spammer detection. Anomalous nodes in the graph not only impact their own communities but also create a ripple effect on neighbors throughout the graph structure. Detecting anomalous nodes in complex graphs has been a challenging task. While existing GAD methods assume all labels are correct, real-world scenarios often involve inaccurate annotations. These noisy labels can severely degrade GAD performance because, with anomalies representing a minority class, even a small number of mislabeled instances can disproportionately interfere with detection models. Cutting edges to mitigate the negative effects of noisy labels is a good option; however, it has both positive and negative influences and also presents an issue of weak supervision. To perform effective GAD with noisy labels, we propose REinforced Graph Anomaly Detector (REGAD) by pruning the edges of candidate nodes potentially with mistaken labels. Moreover, we design the performance feedback based on strategically crafted confident labels to guide the cutting process, ensuring optimal results. Specifically, REGAD contains two novel components. (i) A tailored policy network, which involves two-step actions to remove negative effect propagation step by step. (ii) A policy-in-the-loop mechanism to identify suitable edge removal strategies that control the propagation of noise on the graph and estimate the updated structure to obtain reliable pseudo labels iteratively. Experiments on three real-world datasets demonstrate that REGAD outperforms all baselines under different noisy ratios.

cs.LG↗

arXiv2026

Mesoscale flows in active baths dictate the dynamics of semi-flexible filaments

Semi-flexible filaments in living systems are constantly driven by active forces that often organize into mesoscale coherent flows. Although theory and simulations predict rich filament dynamics, experimental studies of passive filaments in collective active baths remain scarce. Here we present an experimental study on passive colloidal filaments confined to the air-liquid interface beneath a free-standing, quasi-two-dimensional bacterial film featuring jet-like mesoscale flows. By varying filament contour length and bacterial activity, we demonstrate that filament dynamics are governed by its length relative to the characteristic size of the bath. Filaments shorter than the jet width exhibit greatly enhanced translation and rotation with minimal deformation, while long filaments show dramatic deformation but less enhanced transport. We explain our findings through the competition between the active viscous drag of the bath and passive elastic resistance of the filaments, using a modified elastoviscous number that considers the mesoscale flows.

cond-mat.soft↗

arXiv2025

MeCaMIL: Causality-Aware Multiple Instance Learning for Fair and Interpretable Whole Slide Image Diagnosis

Multiple instance learning (MIL) has emerged as the dominant paradigm for whole slide image (WSI) analysis in computational pathology, achieving strong diagnostic performance through patch-level feature aggregation. However, existing MIL methods face critical limitations: (1) they rely on attention mechanisms that lack causal interpretability, and (2) they fail to integrate patient demographics (age, gender, race), leading to fairness concerns across diverse populations. These shortcomings hinder clinical translation, where algorithmic bias can exacerbate health disparities. We introduce \textbf{MeCaMIL}, a causality-aware MIL framework that explicitly models demographic confounders through structured causal graphs. Unlike prior approaches treating demographics as auxiliary features, MeCaMIL employs principled causal inference -- leveraging do-calculus and collider structures -- to disentangle disease-relevant signals from spurious demographic correlations. Extensive evaluation on three benchmarks demonstrates state-of-the-art performance across CAMELYON16 (ACC/AUC/F1: 0.939/0.983/0.946), TCGA-Lung (0.935/0.979/0.931), and TCGA-Multi (0.977/0.993/0.970, five cancer types). Critically, MeCaMIL achieves superior fairness -- demographic disparity variance drops by over 65% relative reduction on average across attributes, with notable improvements for underserved populations. The framework generalizes to survival prediction (mean C-index: 0.653, +0.017 over best baseline across five cancer types). Ablation studies confirm causal graph structure is essential -- alternative designs yield 0.048 lower accuracy and 4.2x times worse fairness. These results establish MeCaMIL as a principled framework for fair, interpretable, and clinically actionable AI in digital pathology. Code will be released upon acceptance.

cs.CV↗

arXiv2025

Introducing LongCat-Flash-Thinking: A Technical Report

We present LongCat-Flash-Thinking, an efficient 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model. Its advanced capabilities are cultivated through a meticulously crafted training process, beginning with long Chain-of-Thought (CoT) data cold-start and culminating in large-scale Reinforcement Learning (RL). We first employ a well-designed cold-start training strategy, which significantly enhances the reasoning potential and equips the model with specialized skills in both formal and agentic reasoning. Then, a core innovation is our domain-parallel training scheme, which decouples optimization across distinct domains (e.g., STEM, Code, Agentic) and subsequently fuses the resulting expert models into a single, nearly Pareto-optimal model. This entire process is powered by our Dynamic ORchestration for Asynchronous rollout (DORA) system, a large-scale RL framework that delivers a greater than threefold training speedup over synchronous methods on tens of thousands of accelerators. As a result, LongCat-Flash-Thinking achieves state-of-the-art performance among open-source models on a suite of complex reasoning tasks. The model exhibits exceptional efficiency in agentic reasoning, reducing average token consumption by 64.5% (from 19, 653 to 6, 965) on AIME-25, without degrading task accuracy. We release LongCat-Flash-Thinking to promote further advances in reasoning systems and agentic AI research.

cs.AI↗

arXiv2025

AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction

Recent progress in large language model (LLM)-based multi-agent collaboration highlights the power of structured communication in enabling collective intelligence. However, existing methods largely rely on static or graph-based inter-agent topologies, lacking the potential adaptability and flexibility in communication. In this work, we propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure, offering a significantly larger topology space for multi-agent communication. Our method focuses on two key directions: (1) Next-Agent Prediction, which selects the most suitable agent role at each step, and (2) Next-Context Selection (NCS), which enables each agent to selectively access relevant information from any previous step. Together, these components construct task-adaptive communication pipelines that support both role flexibility and global information flow. Extensive evaluations across multiple benchmarks demonstrate that our approach achieves superior performance while substantially reducing communication overhead.

cs.AI↗

arXiv2025

AMO-Bench: Large Language Models Still Struggle in High School Math Competitions

We present AMO-Bench, an Advanced Mathematical reasoning benchmark with Olympiad level or even higher difficulty, comprising 50 human-crafted problems. Existing benchmarks have widely leveraged high school math competitions for evaluating mathematical reasoning capabilities of large language models (LLMs). However, many existing math competitions are becoming less effective for assessing top-tier LLMs due to performance saturation (e.g., AIME24/25). To address this, AMO-Bench introduces more rigorous challenges by ensuring all 50 problems are (1) cross-validated by experts to meet at least the International Mathematical Olympiad (IMO) difficulty standards, and (2) entirely original problems to prevent potential performance leakages from data memorization. Moreover, each problem in AMO-Bench requires only a final answer rather than a proof, enabling automatic and robust grading for evaluation. Experimental results across 26 LLMs on AMO-Bench show that even the best-performing model achieves only 52.4% accuracy on AMO-Bench, with most LLMs scoring below 40%. Beyond these poor performances, our further analysis reveals a promising scaling trend with increasing test-time compute on AMO-Bench. These results highlight the significant room for improving the mathematical reasoning in current LLMs. We release AMO-Bench to facilitate further research into advancing the reasoning abilities of language models. https://amo-bench.github.io/

cs.CL↗

arXiv2025

Benchmarking GPT-5 for biomedical natural language processing

Biomedical literature and clinical narratives pose multifaceted challenges for natural language understanding, from precise entity extraction and document synthesis to multi-step diagnostic reasoning. This study extends a unified benchmark to evaluate GPT-5 and GPT-4o under zero-, one-, and five-shot prompting across five core biomedical NLP tasks: named entity recognition, relation extraction, multi-label document classification, summarization, and simplification, and nine expanded biomedical QA datasets covering factual knowledge, clinical reasoning, and multimodal visual understanding. Using standardized prompts, fixed decoding parameters, and consistent inference pipelines, we assessed model performance, latency, and token-normalized cost under official pricing. GPT-5 consistently outperformed GPT-4o, with the largest gains on reasoning-intensive datasets such as MedXpertQA and DiagnosisArena and stable improvements in multimodal QA. In core tasks, GPT-5 achieved better chemical NER and ChemProt scores but remained below domain-tuned baselines for disease NER and summarization. Despite producing longer outputs, GPT-5 showed comparable latency and 30 to 50 percent lower effective cost per correct prediction. Fine-grained analyses revealed improvements in diagnosis, treatment, and reasoning subtypes, whereas boundary-sensitive extraction and evidence-dense summarization remain challenging. Overall, GPT-5 approaches deployment-ready performance for biomedical QA while offering a favorable balance of accuracy, interpretability, and economic efficiency. The results support a tiered prompting strategy: direct prompting for large-scale or cost-sensitive applications, and chain-of-thought scaffolds for analytically complex or high-stakes scenarios, highlighting the continued need for hybrid solutions where precision and factual fidelity are critical.

cs.CL↗

arXiv2025

Quantized Large Language Models in Biomedical Natural Language Processing: Evaluation and Recommendation

Large language models have demonstrated remarkable capabilities in biomedical natural language processing, yet their rapid growth in size and computational requirements present a major barrier to adoption in healthcare settings where data privacy precludes cloud deployment and resources are limited. In this study, we systematically evaluated the impact of quantization on 12 state-of-the-art large language models, including both general-purpose and biomedical-specific models, across eight benchmark datasets covering four key tasks: named entity recognition, relation extraction, multi-label classification, and question answering. We show that quantization substantially reduces GPU memory requirements-by up to 75%-while preserving model performance across diverse tasks, enabling the deployment of 70B-parameter models on 40GB consumer-grade GPUs. In addition, domain-specific knowledge and responsiveness to advanced prompting methods are largely maintained. These findings provide significant practical and guiding value, highlighting quantization as a practical and effective strategy for enabling the secure, local deployment of large yet high-capacity language models in biomedical contexts, bridging the gap between technical advances in AI and real-world clinical translation.

cs.CL↗

arXiv2025

Testing a New Star Formation History Model from Principal Component Analysis to Facilitate Spectral Synthesis Modeling

The spectrum of a galaxy is a complicated convolution of many properties of the galaxy, such as the star formation history (SFH), initial mass function, and metallicity. Inferring galaxy properties from the observed spectrum via spectral synthesis modeling is thus challenging. In particular, a simple yet flexible model for the SFH is required to obtain unbiased inferences. In this paper, we use SFHs from the IllustrisTNG and EAGLE simulations to test SFH models in terms of their capability of describing the simulated SFHs and the spectra generated from them. In addition to some commonly used SFH models ($Γ$, $τ$, and nonparametric), we also examine a model developed from principal component analysis (PCA), trained by a set of SFHs from IllustrisTNG. We find that when using the first five principal components (eigenhistories), the PCA-based models can achieve a good balance between simplicity and accuracy. Among the models tested, the PCA-based model provides high flexibility, by capturing diverse and complex simulated SFHs. To accurately reproduce spectra generated from the simulated SFHs, it is necessary to have a degree of freedom to describe the most recent SFH (e.g., a step function covering the age of 0 - 0.3 Gyr). Overall, the PCA+step model performs well in capturing the diversity of SFHs and reproducing the associated spectra, suggesting it is a promising and reliable approach for spectral synthesis modeling.

astro-ph.GA↗

arXiv2025

Automating Expert-Level Medical Reasoning Evaluation of Large Language Models

As large language models (LLMs) become increasingly integrated into clinical decision-making, ensuring transparent and trustworthy reasoning is essential. However, existing evaluation strategies of LLMs' medical reasoning capability either suffer from unsatisfactory assessment or poor scalability, and a rigorous benchmark remains lacking. To address this, we introduce MedThink-Bench, a benchmark designed for rigorous, explainable, and scalable assessment of LLMs' medical reasoning. MedThink-Bench comprises 500 challenging questions across ten medical domains, each annotated with expert-crafted step-by-step rationales. Building on this, we propose LLM-w-Ref, a novel evaluation framework that leverages fine-grained rationales and LLM-as-a-Judge mechanisms to assess intermediate reasoning with expert-level fidelity while maintaining scalability. Experiments show that LLM-w-Ref exhibits a strong positive correlation with expert judgments. Benchmarking twelve state-of-the-art LLMs, we find that smaller models (e.g., MedGemma-27B) can surpass larger proprietary counterparts (e.g., OpenAI-o3). Overall, MedThink-Bench offers a foundational tool for evaluating LLMs' medical reasoning, advancing their safe and responsible deployment in clinical practice.

cs.CL↗

arXiv2025

Large Language Models for Disease Diagnosis: A Scoping Review

Automatic disease diagnosis has become increasingly valuable in clinical practice. The advent of large language models (LLMs) has catalyzed a paradigm shift in artificial intelligence, with growing evidence supporting the efficacy of LLMs in diagnostic tasks. Despite the increasing attention in this field, a holistic view is still lacking. Many critical aspects remain unclear, such as the diseases and clinical data to which LLMs have been applied, the LLM techniques employed, and the evaluation methods used. In this article, we perform a comprehensive review of LLM-based methods for disease diagnosis. Our review examines the existing literature across various dimensions, including disease types and associated clinical specialties, clinical data, LLM techniques, and evaluation methods. Additionally, we offer recommendations for applying and evaluating LLMs for diagnostic tasks. Furthermore, we assess the limitations of current research and discuss future directions. To our knowledge, this is the first comprehensive review for LLM-based disease diagnosis.

cs.CL↗

arXiv2025

Two categories of UV-upturn galaxies revealed by semi-analytic models

UV-upturn galaxies are characterized by unusually excessive flux in the far-ultraviolet (FUV) band, observed in some elliptical galaxies and the bulges of disk galaxies. We examine UV-upturn galaxies within the semi-analytic model GABE, which embeds the formation of extreme horizontal branch (EHB) stars -- proposed as key candidates responsible for the UV-upturn phenomenon. We have analyzed all related physical processes, including stellar evolution, initial mass functions (IMFs), dust attenuation, galaxy age, metallicity, and binary fractions, in an effort to determine which processes play significant roles. Our findings reveal two categories of UV-upturn galaxies in the semi-analytic model, each with distinct formation channels: old metal-rich quenched elliptical galaxies, which are intrinsic UV-upturn galaxies induced by EHB stars within their old stellar populations, and dusty star-forming galaxies, which are relatively young and may also be photometrically identified as UV-upturn galaxies when accounting for dust attenuation. Dust attenuation contributes to 20% - 60% of the UV-upturn galaxies, depending on the specific dust attenuation models adopted. With the binary star formation model of EHB stars, both of these formation channels exhibit strong preferences for high stellar metallicity. The high-mass end slope of the IMFs is found to have a marginal effect, indicating that a universal IMF is adequate for studying the UV-upturn phenomenon.

astro-ph.GA↗

arXiv2025

Uncertainty-Aware Large Language Models for Explainable Disease Diagnosis

Explainable disease diagnosis, which leverages patient information (e.g., signs and symptoms) and computational models to generate probable diagnoses and reasonings, offers clear clinical values. However, when clinical notes encompass insufficient evidence for a definite diagnosis, such as the absence of definitive symptoms, diagnostic uncertainty usually arises, increasing the risk of misdiagnosis and adverse outcomes. Although explicitly identifying and explaining diagnostic uncertainties is essential for trustworthy diagnostic systems, it remains under-explored. To fill this gap, we introduce ConfiDx, an uncertainty-aware large language model (LLM) created by fine-tuning open-source LLMs with diagnostic criteria. We formalized the task and assembled richly annotated datasets that capture varying degrees of diagnostic ambiguity. Evaluating ConfiDx on real-world datasets demonstrated that it excelled in identifying diagnostic uncertainties, achieving superior diagnostic performance, and generating trustworthy explanations for diagnoses and uncertainties. To our knowledge, this is the first study to jointly address diagnostic uncertainty recognition and explanation, substantially enhancing the reliability of automatic diagnostic systems.

cs.CL↗

arXiv2025

Retrieval-augmented in-context learning for multimodal large language models in disease classification

Objectives: We aim to dynamically retrieve informative demonstrations, enhancing in-context learning in multimodal large language models (MLLMs) for disease classification. Methods: We propose a Retrieval-Augmented In-Context Learning (RAICL) framework, which integrates retrieval-augmented generation (RAG) and in-context learning (ICL) to adaptively select demonstrations with similar disease patterns, enabling more effective ICL in MLLMs. Specifically, RAICL examines embeddings from diverse encoders, including ResNet, BERT, BioBERT, and ClinicalBERT, to retrieve appropriate demonstrations, and constructs conversational prompts optimized for ICL. We evaluated the framework on two real-world multi-modal datasets (TCGA and IU Chest X-ray), assessing its performance across multiple MLLMs (Qwen, Llava, Gemma), embedding strategies, similarity metrics, and varying numbers of demonstrations. Results: RAICL consistently improved classification performance. Accuracy increased from 0.7854 to 0.8368 on TCGA and from 0.7924 to 0.8658 on IU Chest X-ray. Multi-modal inputs outperformed single-modal ones, with text-only inputs being stronger than images alone. The richness of information embedded in each modality will determine which embedding model can be used to get better results. Few-shot experiments showed that increasing the number of retrieved examples further enhanced performance. Across different similarity metrics, Euclidean distance achieved the highest accuracy while cosine similarity yielded better macro-F1 scores. RAICL demonstrated consistent improvements across various MLLMs, confirming its robustness and versatility. Conclusions: RAICL provides an efficient and scalable approach to enhance in-context learning in MLLMs for multimodal disease classification.

cs.AI↗

arXiv2025

Mapping Dust Attenuation at Kiloparsec Scales. II. Attenuation Curves from Near-Ultraviolet to Near-Infrared

This is the second paper in a series that utilize IFS from MaNGA, NUV imaging from Swift/UVOT and NIR imaging from 2MASS to study dust attenuation properties on kpc scales in nearby galaxies. We apply the method developed in Paper I (Zhou et al. 2023) to the updated SWiM_v4.2 catalog, and measure the optical attenuation curve and the attenuation in three NUV bands for 2487 spaxels selected from 91 galaxies with S/N>20 and $A_V$>0.25. We classify all spaxels into two subsets: star-forming (SF) regions and non-SF regions. We explore the correlations of optical opacity ($A_V$) and the optical and NUV slopes of attenuation curves ($A_B/A_V$ and $A_{w2}/A_{w1}$) with a broad range of stellar and emission-line properties, including specific surface brightness of H$α$ emission, stellar age, stellar and gas-phase metallicity, and diagnostics of recent star formation history. When comparing SF and non-SF regions, we find that $A_V$ and $A_B/A_V$ exhibit similar correlations with all the stellar population and emission-line properties considered, while the NUV slopes in SF regions tend to be flatter than those in non-SF regions. The NUV slope $A_{w2}/A_{w1}$ exhibits an anti-correlation with specific surface brightness of H$α$ emission, a trend that is primarily driven by the positive correlation between $A_{w2}/A_{w1}$ and $Σ_\ast$. The NUV slope flattens in SF regions that contain young stellar populations and have experienced recent star formation, but it shows no obvious dependence on stellar or gas-phase metallicity. The spatially resolved dust attenuation properties exhibit no clear correlations with the inclination of host galaxies or the galactocentric distance of the regions. This finding reinforces the conclusion from Paper I that dust attenuation is primarily regulated by local processes on kpc scales or smaller, rather than by global processes at galactic scales.

astro-ph.GA↗

arXiv2025

EPEE: Towards Efficient and Effective Foundation Models in Biomedicine

Foundation models, including language models, e.g., GPT, and vision models, e.g., CLIP, have significantly advanced numerous biomedical tasks. Despite these advancements, the high inference latency and the "overthinking" issues in model inference impair the efficiency and effectiveness of foundation models, thus limiting their application in real-time clinical settings. To address these challenges, we proposed EPEE (Entropy- and Patience-based Early Exiting), a novel hybrid strategy designed to improve the inference efficiency of foundation models. The core idea was to leverage the strengths of entropy-based and patience-based early exiting methods to overcome their respective weaknesses. To evaluate EPEE, we conducted experiments on three core biomedical tasks-classification, relation extraction, and event extraction-using four foundation models (BERT, ALBERT, GPT-2, and ViT) across twelve datasets, including clinical notes and medical images. The results showed that EPEE significantly reduced inference time while maintaining or improving accuracy, demonstrating its adaptability to diverse datasets and tasks. EPEE addressed critical barriers to deploying foundation models in healthcare by balancing efficiency and effectiveness. It potentially provided a practical solution for real-time clinical decision-making with foundation models, supporting reliable and efficient workflows.

cs.AI↗