arXiv subjects

Yifan Gao

Publications and source records attributed to Yifan Gao.

At least 55 records · Page 3Linked to original sources

arXiv2026

SemiTooth: a Generalizable Semi-supervised Framework for Multi-Source Tooth Segmentation

With the rapid advancement of artificial intelligence, intelligent dentistry for clinical diagnosis and treatment has become increasingly promising. As the primary clinical dentistry task, tooth structure segmentation for Cone-Beam Computed Tomography (CBCT) has made significant progress in recent years. However, challenges arise from the obtainment difficulty of full-annotated data, and the acquisition variability of multi-source data across different institutions, which have caused low-quality utilization, voxel-level inconsistency, and domain-specific disparity in CBCT slices. Thus, the rational and efficient utilization of multi-source and unlabeled data represents a pivotal problem. In this paper, we propose SemiTooth, a generalizable semi-supervised framework for multi-source tooth segmentation. Specifically, we first compile MS3Toothset, Multi-Source Semi-Supervised Tooth DataSet for clinical dental CBCT, which contains data from three sources with different-level annotations. Then, we design a multi-teacher and multi-student framework, i.e., SemiTooth, which promotes semi-supervised learning for multi-source data. SemiTooth employs distinct student networks that learn from unlabeled data with different sources, supervised by its respective teachers. Furthermore, a Stricter Weighted-Confidence Constraint is introduced for multiple teachers to improve the multi-source accuracy.Extensive experiments are conducted on MS3Toothset to verify the feasibility and superiority of the SemiTooth framework, which achieves SOTA performance on the semi-supervised and multi-source tooth segmentation scenario.

cs.CV↗

arXiv2026

SynPlanResearch-R1: Encouraging Tool Exploration for Deep Research with Synthetic Plans

Research Agents enable models to gather information from the web using tools to answer user queries, requiring them to dynamically interleave internal reasoning with tool use. While such capabilities can in principle be learned via reinforcement learning with verifiable rewards (RLVR), we observe that agents often exhibit poor exploration behaviors, including premature termination and biased tool usage. As a result, RLVR alone yields limited improvements. We propose SynPlanResearch-R1, a framework that synthesizes tool-use trajectories that encourage deeper exploration to shape exploration during cold-start supervised fine-tuning, providing a strong initialization for subsequent RL. Across seven multi-hop and open-web benchmarks, \framework improves performance by up to 6.0% on Qwen3-8B and 5.8% on Qwen3-4B backbones respectively compared to SOTA baselines. Further analyses of tool-use patterns and training dynamics compared to baselines shed light on the factors underlying these gains. Our code is publicly available at https://github.com/HansiZeng/syn-plan-research.

cs.AI↗

arXiv2026

Realistic tight-binding model for V2Se2O-family altermagnets

Following earlier theoretical prediction, intercalated V2Se2O-family altermagnets such as RbV2Te2O and KV2Se2O have now been experimentally confirmed as d-wave altermagnets, representing the only known van der Waals layered altermagnetic systems. By combining crystal-symmetry-paired spin-momentum locking (CSML) with the layered structure, the V2Se2O-family offers a suitable platform for studying low-dimensional spintronic responses and exploring the interplay among multiple quantum degrees of freedom. To establish a concrete theoretical foundation for understanding and utilizing these materials, we investigate six representative members of the V2Se2O-family and construct a realistic tight-binding model parameterized by first-principles calculations, which is benchmarked by experimental measurements. This model accurately captures essential altermagnetic electronic properties, including CSML and noncollinear spin-conserved currents. It further incorporates strain-coupling parameters, enabling the simulation of strain-tunable responses such as the piezo-Hall effects. This realistic model allows systematic exploration of multiple degrees of freedom (like spin, valley, and layer) within a single system, and lays the groundwork for understanding their coupling with other quantum materials, such as topological insulators and superconductors, thereby advancing both the fundamental understanding and potential device applications of this novel class of layered altermagnets.

cond-mat.mtrl-sci↗

arXiv2026

PRISM: A Framework Harnessing Unsupervised Visual Representations and Textual Prompts for Explainable MACE Survival Prediction from Cardiac Cine MRI

Accurate prediction of major adverse cardiac events (MACE) remains a central challenge in cardiovascular prognosis. We present PRISM (Prompt-guided Representation Integration for Survival Modeling), a self-supervised framework that integrates visual representations from non-contrast cardiac cine magnetic resonance imaging with structured electronic health records (EHRs) for survival analysis. PRISM extracts temporally synchronized imaging features through motion-aware multi-view distillation and modulates them using medically informed textual prompts to enable fine-grained risk prediction. Across four independent clinical cohorts, PRISM consistently surpasses classical survival prediction models and state-of-the-art (SOTA) deep learning baselines under internal and external validation. Further clinical findings demonstrate that the combined imaging and EHR representations derived from PRISM provide valuable insights into cardiac risk across diverse cohorts. Three distinct imaging signatures associated with elevated MACE risk are uncovered, including lateral wall dyssynchrony, inferior wall hypersensitivity, and anterior elevated focus during diastole. Prompt-guided attribution further identifies hypertension, diabetes, and smoking as dominant contributors among clinical and physiological EHR factors.

cs.CV↗

arXiv2026

Electric field switching of altermagnetic spin-splitting in multiferroic skyrmions

Magnetic skyrmions are localized magnetic structures that retain their shape and stability over time, thanks to their topological nature. Recent theoretical and experimental progress has laid the groundwork for understanding magnetic skyrmions characterized by negligible net magnetization and ultrafast dynamics. Notably, skyrmions emerging in materials with altermagnetism, a novel magnetic phase featuring lifted Kramers degeneracy-have remained unreported until now. In this study, we demonstrate that BiFeO3, a multiferroic renowned for its strong coupling between ferroelectricity and magnetism, can transit from a spin cycloid to a Neel-type skyrmion under antidamping spin-orbit torque at room temperature. Strikingly, the altermagnetic spin splitting within BiFeO3 skyrmion can be reversed through the application of an electric field, revealed via the Circular photogalvanic effect. This quasiparticle, which possesses a neutral topological charge, holds substantial promise for diverse applications-most notably, enabling the development of unconventional computing systems with low power consumption and magnetoelectric controllability.

cond-mat.mtrl-sci↗

arXiv2025

HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance

Parameter-Efficient Fine-Tuning (PEFT), especially Low-Rank Adaptation (LoRA), has emerged as a promising approach to fine-tuning large language models(LLMs) while reducing computational and memory overhead. However, LoRA assumes a uniform rank \textit{r} for each incremental matrix, not accounting for the varying significance of weight matrices across different modules and layers. AdaLoRA leverages Singular Value Decomposition (SVD) to parameterize updates and employs pruning of singular values to introduce dynamic rank allocation, thereby enhancing adaptability. However, during the training process, it often encounters issues of slow convergence speed and high computational overhead. To address this issue, we propose HyperAdaLoRA, a novel framework that accelerates the convergence of AdaLoRA by leveraging a hypernetwork. Instead of directly optimizing the components of Singular Value Decomposition $(P, Λ, Q)$, HyperAdaLoRA employs a hypernetwork based on attention mechanisms to dynamically generate these parameters. By pruning the outputs of the hypernetwork that generates the singular values, dynamic rank allocation is achieved. Comprehensive experiments on various datasets and models demonstrate that our method achieves faster convergence without sacrificing performance. Additionally, further extension experiments on other LoRA-based approaches validate the broad applicability of our method.

cs.LG↗

arXiv2025

Intrinsic Moiré Higher-Order Topology Beyond Effective Moiré Lattice Models

Moiré superlattices provide a compelling platform for exploring exotic correlated physics. Electronic interference within these systems often results in flat bands with localized electrons, which are typically described by effective moiré lattice models. While conventional models treat moiré sites as indivisible, analogous to atoms in a crystal, this picture overlooks a crucial distinction: unlike a true atom, a moiré site is composed of tens to thousands of atoms and is therefore spatially divisible. Here, we introduce a universal mechanism rooted in this spatial divisibility to create topological boundary states in moiré materials. Through tight-binding and density functional theory calculations, we demonstrate that cutting a moiré site with a physical boundary induces bulk topological polarization, generating robust boundary states with fractional charges. We further show that when the net edge polarization is canceled, this mechanism drives the system into an intrinsic moiré higher-order topological insulator (mHOTI) phase. As a concrete realization, we predict that twisted bilayer tungsten disulfide ($WS_2$) is a robust mHOTI with experimentally detectable corner states when its boundaries cut through moiré hole sites. Our findings generalize the theoretical framework of moiré higher-order topology, highlight the critical role of edge terminations, and suggest new opportunities for realizing correlated HOTIs and higher-order superconductivity in moiré platforms.

cond-mat.mes-hall↗

arXiv2025

MTRec: Learning to Align with User Preferences via Mental Reward Models

Recommendation models are predominantly trained using implicit user feedback, since explicit feedback is often costly to obtain. However, implicit feedback, such as clicks, does not always reflect users' real preferences. For example, a user might click on a news article because of its attractive headline, but end up feeling uncomfortable after reading the content. In the absence of explicit feedback, such erroneous implicit signals may severely mislead recommender systems. In this paper, we propose MTRec, a novel sequential recommendation framework designed to align with real user preferences by uncovering their internal satisfaction on recommended items. Specifically, we introduce a mental reward model to quantify user satisfaction and propose a distributional inverse reinforcement learning approach to learn it. The learned mental reward model is then used to guide recommendation models to better align with users' real preferences. Our experiments show that MTRec brings significant improvements to a variety of recommendation models. We also deploy MTRec on an industrial short video platform and observe a 7 percent increase in average user viewing time.

cs.IR↗

arXiv2025

Med-K2N: Flexible K-to-N Modality Translation for Medical Image Synthesis

Cross-modal medical image synthesis research focuses on reconstructing missing imaging modalities from available ones to support clinical diagnosis. Driven by clinical necessities for flexible modality reconstruction, we explore K to N medical generation, where three critical challenges emerge: How can we model the heterogeneous contributions of different modalities to various target tasks? How can we ensure fusion quality control to prevent degradation from noisy information? How can we maintain modality identity consistency in multi-output generation? Driven by these clinical necessities, and drawing inspiration from SAM2's sequential frame paradigm and clinicians' progressive workflow of incrementally adding and selectively integrating multi-modal information, we treat multi-modal medical data as sequential frames with quality-driven selection mechanisms. Our key idea is to "learn" adaptive weights for each modality-task pair and "memorize" beneficial fusion patterns through progressive enhancement. To achieve this, we design three collaborative modules: PreWeightNet for global contribution assessment, ThresholdNet for adaptive filtering, and EffiWeightNet for effective weight computation. Meanwhile, to maintain modality identity consistency, we propose the Causal Modality Identity Module (CMIM) that establishes causal constraints between generated images and target modality descriptions using vision-language modeling. Extensive experimental results demonstrate that our proposed Med-K2N outperforms state-of-the-art methods by significant margins on multiple benchmarks. Source code is available.

cs.CV↗

arXiv2025

Arm events in critical planar loop soups

We establish up-to-constants estimates for arm events in the Brownian loop soup on the 2D metric graph associated with the square lattice. More specifically, we consider two natural geometric events: first, ``bulk'' four-arm events, corresponding to two large connected components of loops getting close to each other; and then, two-arm events in the half-plane, used to estimate the probability that a cluster of loops approaches the boundary. Our proof relies on an estimate by Lupu-Werner [Probab. Theory Related Fields 171(3):775-818, 2018], thanks to the well-known coupling between the loop soup and the Gaussian free field on the metric graph [Lecture Notes in Mathematics, volume 2026, 2011] and [Ann. Probab. 44(3):2117-2146, 2016]. As a consequence, we also obtain up-to-constant upper bounds for the corresponding arm events in the random walk loop soup on the square lattice. In this way, we verify Assumptions 5.7 and 5.11 in arXiv:2409.16273: in a box with side length $N$, this implies the existence of crossings where the Gaussian free field remains below $a\sqrt{\log \log N}$ in absolute value, for some constant $a > 0$ large enough.

math.PR↗

arXiv2025

Can Language Models Follow Multiple Turns of Entangled Instructions?

Despite significant achievements in improving the instruction-following capabilities of large language models (LLMs), the ability to process multiple potentially entangled or conflicting instructions remains a considerable challenge. Real-world scenarios often require consistency across multiple instructions over time, such as secret privacy, personal preferences, and prioritization, which demand sophisticated abilities to integrate multiple turns and carefully balance competing objectives when instructions intersect or conflict. This work presents a systematic investigation of LLMs' capabilities in handling multiple turns of instructions, covering three levels of difficulty: (1) retrieving information from instructions, (2) tracking and reasoning across turns, and (3) resolving conflicts among instructions. We construct MultiTurnInstruct~with $\sim$1.1K high-quality multi-turn conversations through the human-in-the-loop approach and result in nine capability categories, including statics and dynamics, reasoning, and multitasking. Our finding reveals an intriguing trade-off between different capabilities. While GPT models demonstrate superior memorization, they show reduced effectiveness in privacy-protection tasks requiring selective information withholding. Larger models exhibit stronger reasoning capabilities but still struggle with resolving conflicting instructions. Importantly, these performance gaps cannot be attributed solely to information loss, as models demonstrate strong BLEU scores on memorization tasks. Still, their attention mechanisms fail to integrate multiple related instructions effectively. These findings highlight critical areas for improvement in complex real-world tasks involving multi-turn instructions. Data and codes are released at https://github.com/Glaciohound/Multi-Turn-Instruct.

cs.CL↗

arXiv2025

A Composite Alignment-Aware Framework for Myocardial Lesion Segmentation in Multi-sequence CMR Images

Accurate segmentation of myocardial lesions from multi-sequence cardiac magnetic resonance imaging is essential for cardiac disease diagnosis and treatment planning. However, achieving optimal feature correspondence is challenging due to intensity variations across modalities and spatial misalignment caused by inconsistent slice acquisition protocols. We propose CAA-Seg, a composite alignment-aware framework that addresses these challenges through a two-stage approach. First, we introduce a selective slice alignment method that dynamically identifies and aligns anatomically corresponding slice pairs while excluding mismatched sections, ensuring reliable spatial correspondence between sequences. Second, we develop a hierarchical alignment network that processes multi-sequence features at different semantic levels, i.e., local deformation correction modules address geometric variations in low-level features, while global semantic fusion blocks enable semantic fusion at high levels where intensity discrepancies diminish. We validate our method on a large-scale dataset comprising 397 patients. Experimental results show that our proposed CAA-Seg achieves superior performance on most evaluation metrics, with particularly strong results in myocardial infarction segmentation, representing a substantial 5.54% improvement over state-of-the-art approaches. The code is available at https://github.com/yifangao112/CAA-Seg.

eess.IV↗

arXiv2025

LRMR: LLM-Driven Relational Multi-node Ranking for Lymph Node Metastasis Assessment in Rectal Cancer

Accurate preoperative assessment of lymph node (LN) metastasis in rectal cancer guides treatment decisions, yet conventional MRI evaluation based on morphological criteria shows limited diagnostic performance. While some artificial intelligence models have been developed, they often operate as black boxes, lacking the interpretability needed for clinical trust. Moreover, these models typically evaluate nodes in isolation, overlooking the patient-level context. To address these limitations, we introduce LRMR, an LLM-Driven Relational Multi-node Ranking framework. This approach reframes the diagnostic task from a direct classification problem into a structured reasoning and ranking process. The LRMR framework operates in two stages. First, a multimodal large language model (LLM) analyzes a composite montage image of all LNs from a patient, generating a structured report that details ten distinct radiological features. Second, a text-based LLM performs pairwise comparisons of these reports between different patients, establishing a relative risk ranking based on the severity and number of adverse features. We evaluated our method on a retrospective cohort of 117 rectal cancer patients. LRMR achieved an area under the curve (AUC) of 0.7917 and an F1-score of 0.7200, outperforming a range of deep learning baselines, including ResNet50 (AUC 0.7708). Ablation studies confirmed the value of our two main contributions: removing the relational ranking stage or the structured prompting stage led to a significant performance drop, with AUCs falling to 0.6875 and 0.6458, respectively. Our work demonstrates that decoupling visual perception from cognitive reasoning through a two-stage LLM framework offers a powerful, interpretable, and effective new paradigm for assessing lymph node metastasis in rectal cancer.

cs.LG↗

arXiv2025

UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations

The rapid advancement of conversational search systems revolutionizes how information is accessed by enabling the multi-turn interaction between the user and the system. Existing conversational search systems are usually built with two different models. This separation restricts the system from leveraging the intrinsic knowledge of the models simultaneously, which cannot ensure the effectiveness of retrieval benefiting the generation. The existing studies for developing unified models cannot fully address the aspects of understanding conversational context, managing retrieval independently, and generating responses. In this paper, we explore how to unify dense retrieval and response generation for large language models in conversation. We conduct joint fine-tuning with different objectives and design two mechanisms to reduce the inconsistency risks while mitigating data discrepancy. The evaluations on five conversational search datasets demonstrate that our unified model can mutually improve both tasks and outperform the existing baselines.

cs.CL↗

arXiv2025

Leveraging Large Language Models for Spontaneous Speech-Based Suicide Risk Detection

Early identification of suicide risk is crucial for preventing suicidal behaviors. As a result, the identification and study of patterns and markers related to suicide risk have become a key focus of current research. In this paper, we present the results of our work in the 1st SpeechWellness Challenge (SW1), which aims to explore speech as a non-invasive and easily accessible mental health indicator for identifying adolescents at risk of suicide.Our approach leverages large language model (LLM) as the primary tool for feature extraction, alongside conventional acoustic and semantic features. The proposed method achieves an accuracy of 74\% on the test set, ranking first in the SW1 challenge. These findings demonstrate the potential of LLM-based methods for analyzing speech in the context of suicide risk assessment.

cs.SD↗

arXiv2025

SafeClick: Error-Tolerant Interactive Segmentation of Any Medical Volumes via Hierarchical Expert Consensus

Foundation models for volumetric medical image segmentation have emerged as powerful tools in clinical workflows, enabling radiologists to delineate regions of interest through intuitive clicks. While these models demonstrate promising capabilities in segmenting previously unseen anatomical structures, their performance is strongly influenced by prompt quality. In clinical settings, radiologists often provide suboptimal prompts, which affects segmentation reliability and accuracy. To address this limitation, we present SafeClick, an error-tolerant interactive segmentation approach for medical volumes based on hierarchical expert consensus. SafeClick operates as a plug-and-play module compatible with foundation models including SAM 2 and MedSAM 2. The framework consists of two key components: a collaborative expert layer (CEL) that generates diverse feature representations through specialized transformer modules, and a consensus reasoning layer (CRL) that performs cross-referencing and adaptive integration of these features. This architecture transforms the segmentation process from a prompt-dependent operation to a robust framework capable of producing accurate results despite imperfect user inputs. Extensive experiments across 15 public datasets demonstrate that our plug-and-play approach consistently improves the performance of base foundation models, with particularly significant gains when working with imperfect prompts. The source code is available at https://github.com/yifangao112/SafeClick.

eess.IV↗

arXiv2025

Aligning Large Language Models with Implicit Preferences from User-Generated Content

Learning from preference feedback is essential for aligning large language models (LLMs) with human values and improving the quality of generated responses. However, existing preference learning methods rely heavily on curated data from humans or advanced LLMs, which is costly and difficult to scale. In this work, we present PUGC, a novel framework that leverages implicit human Preferences in unlabeled User-Generated Content (UGC) to generate preference data. Although UGC is not explicitly created to guide LLMs in generating human-preferred responses, it often reflects valuable insights and implicit preferences from its creators that has the potential to address readers' questions. PUGC transforms UGC into user queries and generates responses from the policy model. The UGC is then leveraged as a reference text for response scoring, aligning the model with these implicit preferences. This approach improves the quality of preference data while enabling scalable, domain-specific alignment. Experimental results on Alpaca Eval 2 show that models trained with DPO and PUGC achieve a 9.37% performance improvement over traditional methods, setting a 35.93% state-of-the-art length-controlled win rate using Mistral-7B-Instruct. Further studies highlight gains in reward quality, domain-specific alignment effectiveness, robustness against UGC quality, and theory of mind capabilities. Our code and dataset are available at https://zhaoxuan.info/PUGC.github.io/

cs.CL↗

arXiv2025

Beyond Pixel Agreement: Large Language Models as Clinical Guardrails for Reliable Medical Image Segmentation

Evaluating AI-generated medical image segmentations for clinical acceptability poses a significant challenge, as traditional pixelagreement metrics often fail to capture true diagnostic utility. This paper introduces Hierarchical Clinical Reasoner (HCR), a novel framework that leverages Large Language Models (LLMs) as clinical guardrails for reliable, zero-shot quality assessment. HCR employs a structured, multistage prompting strategy that guides LLMs through a detailed reasoning process, encompassing knowledge recall, visual feature analysis, anatomical inference, and clinical synthesis, to evaluate segmentations. We evaluated HCR on a diverse dataset across six medical imaging tasks. Our results show that HCR, utilizing models like Gemini 2.5 Flash, achieved a classification accuracy of 78.12%, performing comparably to, and in instances exceeding, dedicated vision models such as ResNet50 (72.92% accuracy) that were specifically trained for this task. The HCR framework not only provides accurate quality classifications but also generates interpretable, step-by-step reasoning for its assessments. This work demonstrates the potential of LLMs, when appropriately guided, to serve as sophisticated evaluators, offering a pathway towards more trustworthy and clinically-aligned quality control for AI in medical imaging.

eess.IV↗