Fan Gao

Zixian Su, Hongkai Zhang, Fan Gao et al.

Multimodal Large Language Models (MLLMs) have shown strong performance on public medical benchmarks, yet existing evaluations often remain weak proxies for clinical use, relying on isolated inputs and simplified recognition-style tasks. We introduce CardioLens, a leakage-resistant evaluation testbed for multi-sequence Cardiovascular Magnetic Resonance (CMR), constructed from private hospital archives through a rigorous report-to-QA construction and verification pipeline. CardioLens contains 473,896 slices and 13,494 verified QA pairs across 4D Cine, LGE, perfusion, and T2-weighted imaging, and evaluates three stages of CMR interpretation: image understanding, report generation, and disease diagnosis. Across 24 state-of-the-art MLLMs, CardioLens reveals a substantial clinical reality gap: models perform poorly overall, with performance degrading along the real CMR workflow. Confusion analysis further shows a category-collapse failure mode, where models default to frequent abnormal categories rather than distinguishing clinically distinct findings. To rule out MLLM-compatible input construction as the primary cause, we compare random, clinically motivated, and data-driven slice selection protocols under different slice budgets; performance changes only marginally, typically by about 1%. Explicit reasoning prompts also fail to rescue performance, often making models more conservative rather than improving visual evidence use. These results show that current MLLMs remain far from reliable CMR interpretation, where clinical decisions require integrating distributed evidence across sequences, views, and temporal phases. CardioLens provides a clinically grounded testbed for developing next-generation MLLMs toward real-world clinical deployment.

Fan Gao, Hang Jiang, Rui Yang et al. · mit

Educational materials such as survey articles in specialized fields like computer science traditionally require tremendous expert inputs and are therefore expensive to create and update. Recently, Large Language Models (LLMs) have achieved significant success across various general tasks. However, their effectiveness and limitations in the education domain are yet to be fully explored. In this work, we examine the proficiency of LLMs in generating succinct survey articles specific to the niche field of NLP in computer science, focusing on a curated list of 99 topics. Automated benchmarks reveal that GPT-4 surpasses its predecessors, inluding GPT-3.5, PaLM2, and LLaMa2 by margins ranging from 2% to 20% in comparison to the established ground truth. We compare both human and GPT-based evaluation scores and provide in-depth analysis. While our findings suggest that GPT-created surveys are more contemporary and accessible than human-authored ones, certain limitations were observed. Notably, GPT-4, despite often delivering outstanding content, occasionally exhibited lapses like missing details or factual errors. At last, we compared the rating behavior between humans and GPT-4 and found systematic bias in using GPT evaluation.

Yutong Liu, Feng Xiao, Ziyue Zhang et al.

Multi-level Tibetan spelling correction addresses errors at both the character and syllable levels within a unified model. Existing methods focus mainly on single-level correction and lack effective integration of both levels. Moreover, there are no open-source datasets or augmentation methods tailored for this task in Tibetan. To tackle this, we propose a data augmentation approach using unlabeled text to generate multi-level corruptions, and introduce TiSpell, a semi-masked model capable of correcting both character- and syllable-level errors. Although syllable-level correction is more challenging due to its reliance on global context, our semi-masked strategy simplifies this process. We synthesize nine types of corruptions on clean sentences to create a robust training set. Experiments on both simulated and real-world data demonstrate that TiSpell, trained on our dataset, outperforms baseline models and matches the performance of state-of-the-art approaches, confirming its effectiveness.

Xinjie Zhao, Moritz Blum, Fan Gao et al.

AGENTiGraph is a user-friendly, agent-driven system that enables intuitive interaction and management of domain-specific data through the manipulation of knowledge graphs in natural language. It gives non-technical users a complete, visual solution to incrementally build and refine their knowledge bases, allowing multi-round dialogues and dynamic updates without specialized query languages. The flexible design of AGENTiGraph, including intent classification, task planning, and automatic knowledge integration, ensures seamless reasoning between diverse tasks. Evaluated on a 3,500-query benchmark within an educational scenario, the system outperforms strong zero-shot baselines (achieving 95.12% classification accuracy, 90.45% execution success), indicating potential scalability to compliance-critical or multi-step queries in legal and medical domains, e.g., incorporating new statutes or research on the fly. Our open-source demo offers a powerful new paradigm for multi-turn enterprise knowledge management that bridges LLMs and structured graphs.

Yutong Liu, Ziyue Zhang, Ban Ma-bao et al.

Tibetan is a low-resource language with minimal parallel speech corpora spanning its three major dialects-Ü-Tsang, Amdo, and Kham-limiting progress in speech modeling. To address this issue, we propose FMSD-TTS, a few-shot, multi-speaker, multi-dialect text-to-speech framework that synthesizes parallel dialectal speech from limited reference audio and explicit dialect labels. Our method features a novel speaker-dialect fusion module and a Dialect-Specialized Dynamic Routing Network (DSDR-Net) to capture fine-grained acoustic and linguistic variations across dialects while preserving speaker identity. Extensive objective and subjective evaluations demonstrate that FMSD-TTS significantly outperforms baselines in both dialectal expressiveness and speaker similarity. We further validate the quality and utility of the synthesized speech through a challenging speech-to-speech dialect conversion task. Our contributions include: (1) a novel few-shot TTS system tailored for Tibetan multi-dialect speech synthesis, (2) the public release of a large-scale synthetic Tibetan speech corpus generated by FMSD-TTS, and (3) an open-source evaluation toolkit for standardized assessment of speaker similarity, dialect consistency, and audio quality.

Cheng Huang, Fan Gao, Yutong Liu et al.

Advancement of large language models (LLMs) has brought transformative capabilities to NLP, but such progress remains unevenly distributed, especially for low-resource and culturally rich languages like Tibetan. In this paper, we present TIB-STC, the first large-scale, expert-curated, and multi-domain dataset specifically designed to support the development and evaluation of LLMs for the Tibetan language. Spanning over 11 billion tokens across literature, religion, medicine, law, and daily communication, TIB-STC preserves traditional grammar and stylistic richness. To validate its utility, we train a reference model, Sun-Shine, on TIB-STC through a three-stage pipeline involving pretraining, supervised fine-tuning, and preference optimization. Evaluation on TLUE Benchmark for Tibetan-specific tasks, including Ti-MMLU and Ti-SafetyBench, demonstrates the TIB-STC's effectiveness in enabling robust instruction-following and culturally aligned generation. We release TIB-STC to advance research in low-resource language modeling and promote inclusivity in multilingual NLP. All data are available: https://github.com/Vicentvankor/sun-shine.

Ding Xia, Xinyue Gui, Mark Colley et al.

Automated vehicles lack natural communication channels with other road users, making external Human-Machine Interfaces (eHMIs) essential for conveying intent and maintaining trust in shared environments. However, most eHMI studies rely on developer-crafted message-action pairs, which are difficult to adapt to diverse and dynamic traffic contexts. A promising alternative is to use Large Language Models (LLMs) as action designers that generate context-conditioned eHMI actions, yet such designers lack perceptual verification and typically depend on fixed prompts or costly human-annotated feedback for improvement. We present See2Refine, a human-free, closed-loop framework that uses vision-language model (VLM) perceptual evaluation as automated visual feedback to improve an LLM-based eHMI action designer. Given a driving context and a candidate eHMI action, the VLM evaluates the perceived appropriateness of the action, and this feedback is used to iteratively revise the designer's outputs, enabling systematic refinement without human supervision. We evaluate our framework across three eHMI modalities (lightbar, eyes, and arm) and multiple LLM model sizes. Across settings, our framework consistently outperforms prompt-only LLM designers and manually specified baselines in both VLM-based metrics and human-subject evaluations. Results further indicate that the improvements generalize across modalities and that VLM evaluations are well aligned with human preferences, supporting the robustness and effectiveness of See2Refine for scalable action design.

Fan Gao, Cheng Huang, Nyima Tashi et al.

To address the severe data scarcity in Tibetan, a low-resource language spoken by over six million people, we introduce TIBSTC-CoT, the large-scale, multi-domain Tibetan dataset automatically constructed via chain-of-thought prompting with large language models (LLMs). TIBSTC-CoT establishes a scalable and reproducible framework for dataset creation in low-resource settings, covering diverse domains and reasoning patterns essential for language understanding and generation. Building on this dataset, we develop the Sunshine-thinking LLM family, a series of Tibetan-centric LLMs equipped with chain-of-thought capabilities. Trained entirely on TIBSTC-CoT, Sunshine-thinking has demonstrated strong reasoning and generation performance, comparable to state-of-the-art (SOTA) multilingual LLMs. Our work marks a significant step toward inclusive AI by enabling high-quality Tibetan language processing through both resource creation and model innovation. All data are available: https://github.com/Vicentvankor/sun-shine.

Cheng Huang, Weizheng Xie, Fan Gao et al.

Structural changes in retinal blood vessels are critical biomarkers for the onset and progression of glaucoma and other ocular diseases. However, current vessel segmentation approaches largely rely on supervised learning and extensive manual annotations, which are costly, error-prone, and difficult to obtain in optical coherence tomography angiography. Here we present BioVessel-Net, an unsupervised generative framework that integrates vessel biostatistics with adversarial refinement and a radius-guided segmentation strategy. Unlike pixel-based methods, BioVessel-Net directly models vascular structures with biostatistical coherence, achieving accurate and explainable vessel extraction without labeled data or high-performance computing. To support training and evaluation, we introduce RetinaMix, a new benchmark dataset of 2D and 3D OCTA images with high-resolution vessel details from diverse populations. Experimental results demonstrate that BioVessel-Net achieves near-perfect segmentation accuracy across RetinaMix and existing datasets, substantially outperforming state-of-the-art supervised and semi-supervised methods. Together, BioVessel-Net and RetinaMix provide a label-free, computationally efficient, and clinically interpretable solution for retinal vessel analysis, with broad potential for glaucoma monitoring, blood flow modeling, and progression prediction. Code and dataset are available: https://github.com/VikiXie/SatMar8.

Yibo Zhao, Fan Gao, Youcheng Cai et al.

3D Gaussian Splatting (3DGS) enables high-quality real-time 3D rendering but faces challenges in efficiently scaling to ultra-dense scenes and high-resolution due to computational bottlenecks that limit its use in latency-sensitive applications. Instead of optimizing the splatting pipeline itself, we propose \textbf{3DGS$^3$}, a unified post-rendering framework that jointly performs super sampling and frame interpolation through differentiable processing of low-resolution outputs to achieve both high-resolution and high-frame-rate rendering. Our \textbf{Gradient\- \-Aware Super Sampling (GASS)} module leverages the continuous differentiability of 3DGS to extract image gradients that guide a GRU-based refinement network to enable high-fidelity super sampling. Furthermore, a \textbf{Lightweight Temporal Frame Interpolation (LTFI)} module based on a compact U-Net-like backbone fuses temporal and differentiable spatial cues from consecutive frames to synthesize temporally coherent intermediate frames. Experiments on public datasets demonstrate that 3DGS$^3$ achieves superior rendering efficiency and visual quality when compared with state-of-the-art methods and remains compatible with existing 3DGS acceleration techniques. The code will be publicly released upon acceptance.

Fan Gao, Sherry T. Tong, Jiwoong Sohn et al.

While reasoning-enhanced large language models perform strongly on English medical tasks, a persistent multilingual gap remains, with substantially weaker reasoning in local languages, limiting equitable global medical deployment. To bridge this gap, we introduce Med-CoReasoner, a language-informed co-reasoning framework that elicits parallel English and local-language reasoning, abstracts them into structured concepts, and integrates local clinical knowledge into an English logical scaffold via concept-level alignment and retrieval. This design combines the structural robustness of English reasoning with the practice-grounded expertise encoded in local languages. To evaluate multilingual medical reasoning beyond multiple-choice settings, we construct MultiMed-X, a benchmark covering seven languages with expert-annotated long-form question answering and natural language inference tasks, comprising 350 instances per language. Experiments across three benchmarks show that Med-CoReasoner improves multilingual reasoning performance by an average of 5%, with particularly substantial gains in low-resource languages. Moreover, model distillation and expert evaluation analysis further confirm that Med-CoReasoner produces clinically sound and culturally grounded reasoning traces.

Weihao Xuan, Rui Yang, Heli Qi et al.

Existing large language model (LLM) evaluation benchmarks primarily focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-linguistic reasoning abilities. This dual limitation makes it challenging to comprehensively assess LLMs' performance in the multilingual setting. To fill this gap, we introduce MMLU-ProX, a comprehensive benchmark covering 29 languages, built on an English benchmark. Each language version consists of 11,829 identical questions, enabling direct cross-linguistic comparisons. Additionally, to meet efficient evaluation needs, we provide a lite version containing 658 questions per language. To ensure the high quality of MMLU-ProX, we employ a rigorous development process that involves multiple powerful LLMs for translation, followed by expert review to ensure accurate expression, consistent terminology, and cultural relevance. Building on this, we systematically evaluate 36 state-of-the-art LLMs, including reasoning-enhanced and multilingual-optimized LLMs. The results reveal significant disparities in the multilingual capabilities of LLMs: While they perform well in high-resource languages, their performance declines markedly in low-resource languages, with gaps of up to 24.3%. Through MMLU-ProX, we aim to advance the development of more inclusive AI systems and promote equitable access to technology across global contexts.

Jiacheng Tang, Nankai Wu, Fan Gao et al.

Metaphorical expressions are abundant in Traditional Chinese Medicine (TCM), conveying complex disease mechanisms and holistic health concepts through culturally rich and often abstract terminology. Bridging these metaphors to anatomically driven Western medical (WM) concepts poses significant challenges for both automated language processing and real-world clinical practice. To address this gap, we propose a novel multi-agent and chain-of-thought (CoT) framework designed to interpret TCM metaphors accurately and map them to WM pathophysiology. Specifically, our approach combines domain-specialized agents (TCM Expert, WM Expert) with a Coordinator Agent, leveraging stepwise chain-of-thought prompts to ensure transparent reasoning and conflict resolution. We detail a methodology for building a metaphor-rich TCM dataset, discuss strategies for effectively integrating multi-agent collaboration and CoT reasoning, and articulate the theoretical underpinnings that guide metaphor interpretation across distinct medical paradigms. We present a comprehensive system design and highlight both the potential benefits and limitations of our approach, while leaving placeholders for future experimental validation. Our work aims to support clinical decision-making, cross-system educational initiatives, and integrated healthcare research, ultimately offering a robust scaffold for reconciling TCM's symbolic language with the mechanistic focus of Western medicine.

Fan Gao, Cheng Huang, Nyima Tashi et al.

Large language models have made tremendous progress in recent years, but low-resource languages, like Tibetan, remain significantly underrepresented in their evaluation. Despite Tibetan being spoken by over seven million people, it has largely been neglected in the development and assessment of large language models. To address this gap, we present a \textbf{T}ibetan \textbf{L}anguage \textbf{U}nderstanding \textbf{E}valuation Benchmark, \textbf{TLUE}, the first large-scale benchmark for measuring the proficiency of LLMs in the Tibetan language. \textbf{TLUE} comprises two major components: a comprehensive multi-task understanding benchmark spanning 5 domains and 67 subdomains, and a safety benchmark encompassing 7 subdomains. Then, we evaluate a diverse set of state-of-the-art large language models. Experimental results demonstrate that most large language models perform below the random baseline, highlighting the considerable challenges they face in Tibetan language processing. \textbf{TLUE} provides a crucial foundation for advancing future research in Tibetan language understanding and highlights the importance of promoting greater inclusivity in the development of large language models.

Xinjie Zhao, Fan Gao, Xingyu Song et al.

Recent advances in large language models (LLMs) have significantly improved multi-hop question answering (QA) through direct Chain-of-Thought (CoT) reasoning. However, the irreversible nature of CoT leads to error accumulation, making it challenging to correct mistakes in multi-hop reasoning. This paper introduces ReAgent: a Reversible multi-Agent collaborative framework augmented with explicit backtracking mechanisms, enabling reversible multi-hop reasoning. By incorporating text-based retrieval, information aggregation and validation, our system can detect and correct errors mid-reasoning, leading to more robust and interpretable QA outcomes. The framework and experiments serve as a foundation for future work on error-tolerant QA systems. Empirical evaluations across three benchmarks indicate ReAgent's efficacy, yielding average about 6\% improvements against baseline models.

Yujing Wang, Yiren Chen, Huoran Li et al.

As global e-commerce platforms continue to expand, companies are entering new markets where they encounter cold-start challenges due to limited human labels and user behaviors. In this paper, we share our experiences in Coupang to provide a competitive cold-start performance of relevance matching for emerging e-commerce markets. Specifically, we present a Cold-Start Relevance Matching (CSRM) framework, utilizing a multilingual Large Language Model (LLM) to address three challenges: (1) activating cross-lingual transfer learning abilities of LLMs through machine translation tasks; (2) enhancing query understanding and incorporating e-commerce knowledge by retrieval-based query augmentation; (3) mitigating the impact of training label errors through a multi-round self-distillation training strategy. Our experiments demonstrate the effectiveness of CSRM-LLM and the proposed techniques, resulting in successful real-world deployment and significant online gains, with a 45.8% reduction in defect ratio and a 0.866% uplift in session purchase rate.

Fan Gao, Xinjie Zhao, Ding Xia et al.

Seeking dietary guidance often requires navigating complex professional knowledge while accommodating individual health conditions. Knowledge Graphs (KGs) offer structured and interpretable nutritional information, whereas Large Language Models (LLMs) naturally facilitate conversational recommendation delivery. In this paper, we present HealthGenie, an interactive system that combines the strengths of LLMs and KGs to provide personalized dietary recommendations along with hierarchical information visualization for a quick and intuitive overview. Upon receiving a user query, HealthGenie performs query refinement and retrieves relevant information from a pre-built KG. The system then visualizes and highlights pertinent information, organized by defined categories, while offering detailed, explainable recommendation rationales. Users can further tailor these recommendations by adjusting preferences interactively. Our evaluation, comprising a within-subject comparative experiment and an open-ended discussion, demonstrates that HealthGenie effectively supports users in obtaining personalized dietary guidance based on their health conditions while reducing interaction effort and cognitive load. These findings highlight the potential of LLM-KG integration in supporting decision-making through explainable and visualized information. We examine the system's usefulness and effectiveness with an N=12 within-subject study and provide design considerations for future systems that integrate conversational LLM and KG.

Yutong Liu, Ziyue Zhang, Ban Ma-bao et al.

Tibetan is a low-resource language with limited parallel speech corpora spanning its three major dialects (Ü-Tsang, Amdo, and Kham), limiting progress in speech modeling. To address this issue, we propose TMD-TTS, a unified Tibetan multi-dialect text-to-speech (TTS) framework that synthesizes parallel dialectal speech from explicit dialect labels. Our method features a dialect fusion module and a Dialect-Specialized Dynamic Routing Network (DSDR-Net) to capture fine-grained acoustic and linguistic variations across dialects. Extensive objective and subjective evaluations demonstrate that TMD-TTS significantly outperforms baselines in dialectal expressiveness. We further validate the quality and utility of the synthesized speech through a challenging Speech-to-Speech Dialect Conversion (S2SDC) task.

Fan Gao, Dongyuan Li, Ding Xia et al.

Chinese essay writing and its evaluation are critical in educational contexts, yet the capabilities of Large Language Models (LLMs) in this domain remain largely underexplored. Existing benchmarks often rely on coarse-grained text quality metrics, largely overlooking the structural and rhetorical complexities of Chinese essays, particularly across diverse genres. To address this gap, we propose \benchName, a multi-genre benchmark specifically designed for Chinese essay writing across four major genres: Argumentative, Narrative, Descriptive, and Expository. We curate and refine a total of 728 real-world prompts to ensure authenticity and meticulously categorize them into the \textit{Open-Ended} and \textit{Constrained} sets to capture diverse writing scenarios. To reliably evaluate generated essays, we develop a fine-grained, genre-specific scoring framework that hierarchically aggregates scores. We further validate our evaluation protocol through a comprehensive human agreement study. Finally, we benchmark 15 large-sized LLMs, analyzing their strengths and limitations across genres and instruction types. With \benchName, we aim to advance LLM-based Chinese essay evaluation and inspire future research on improving essay generation in educational settings.

Cheng Huang, Nyima Tashi, Fan Gao et al.

Tibetan, one of the major low-resource languages in Asia, presents unique linguistic and sociocultural characteristics that pose both challenges and opportunities for AI research. Despite increasing interest in developing AI systems for underrepresented languages, Tibetan has received limited attention due to a lack of accessible data resources, standardized benchmarks, and dedicated tools. This paper provides a comprehensive survey of the current state of Tibetan AI in the AI domain, covering textual and speech data resources, NLP tasks, machine translation, speech recognition, and recent developments in LLMs. We systematically categorize existing datasets and tools, evaluate methods used across different tasks, and compare performance where possible. We also identify persistent bottlenecks such as data sparsity, orthographic variation, and the lack of unified evaluation metrics. Additionally, we discuss the potential of cross-lingual transfer, multi-modal learning, and community-driven resource creation. This survey aims to serve as a foundational reference for future work on Tibetan AI research and encourages collaborative efforts to build an inclusive and sustainable AI ecosystem for low-resource languages.

Jin Zhang, Fan Gao, Linyu Li et al.

The rise of large language models has led to significant performance breakthroughs in named entity recognition (NER) for high-resource languages, yet there remains substantial room for improvement in low- and medium-resource languages. Existing multilingual NER methods face severe language interference during the multi-language adaptation process, manifested in feature conflicts between different languages and the competitive suppression of low-resource language features by high-resource languages. Although training a dedicated model for each language can mitigate such interference, it lacks scalability and incurs excessive computational costs in real-world applications. To address this issue, we propose RetrieveAll, a universal multilingual NER framework based on dynamic LoRA. The framework decouples task-specific features across languages and demonstrates efficient dynamic adaptability. Furthermore, we introduce a cross-granularity knowledge augmented method that fully exploits the intrinsic potential of the data without relying on external resources. By leveraging a hierarchical prompting mechanism to guide knowledge injection, this approach advances the paradigm from "prompt-guided inference" to "prompt-driven learning." Experimental results show that RetrieveAll outperforms existing baselines; on the PAN-X dataset, it achieves an average F1 improvement of 12.1 percent.

Tsendsuren Munkhdalai, Khe Chai Sim, Angad Chandorkar et al.

Fast contextual adaptation has shown to be effective in improving Automatic Speech Recognition (ASR) of rare words and when combined with an on-device personalized training, it can yield an even better recognition result. However, the traditional re-scoring approaches based on an external language model is prone to diverge during the personalized training. In this work, we introduce a model-based end-to-end contextual adaptation approach that is decoder-agnostic and amenable to on-device personalization. Our on-device simulation experiments demonstrate that the proposed approach outperforms the traditional re-scoring technique by 12% relative WER and 15.7% entity mention specific F1-score in a continues personalization scenario.

Konstantin Shestopaloff, Mei Dong, Fan Gao et al.

Current advances in next generation sequencing techniques have allowed researchers to conduct comprehensive research on microbiome and human diseases, with recent studies identifying associations between human microbiome and health outcomes for a number of chronic conditions. However, microbiome data structure, characterized by sparsity and skewness, presents challenges to building effective classifiers. To address this, we present an innovative approach for distance-based classification using mixture distributions (DCMD). The method aims to improve classification performance when using microbiome community data, where the predictors are composed of sparse and heterogeneous count data. This approach models the inherent uncertainty in sparse counts by estimating a mixture distribution for the sample data, and representing each observation as a distribution, conditional on observed counts and the estimated mixture, which are then used as inputs for distance-based classification. The method is implemented into a k-means and k-nearest neighbours framework and we identify two distance metrics that produce optimal results. The performance of the model is assessed using simulations and applied to a human microbiome study, with results compared against a number of existing machine learning and distance-based approaches. The proposed method is competitive when compared to the machine learning approaches and showed a clear improvement over commonly used distance-based classifiers. The range of applicability and robustness make the proposed method a viable alternative for classification using sparse microbiome count data.