arXiv subjects

Yan Li

Publications and source records attributed to Yan Li.

At least 127 records · Page 7Linked to original sources

arXiv2026

Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning in Unified Multimodal Models

Existing test-time scaling (TTS) methods for unified multimodal models (UMMs) in text-to-image (T2I) generation primarily rely on search or sampling strategies that produce only instance-level improvements, limiting the ability to learn from prior inferences and accumulate knowledge across similar prompts. To overcome these limitations, we propose Meta-TTRL, a metacognitive test-time reinforcement learning framework. Meta-TTRL performs test-time parameter optimization guided by model-intrinsic monitoring signals derived from the meta-knowledge of UMMs, achieving self-improvement and capability-level improvement at test time. Extensive experiments demonstrate that Meta-TTRL generalizes well across three representative UMMs, including Janus-Pro-7B, BAGEL, and Qwen-Image, achieving significant gains on compositional reasoning tasks and multiple T2I benchmarks with limited data. We provide the first comprehensive analysis to investigate the potential of test-time reinforcement learning (TTRL) for T2I generation in UMMs. Our analysis further reveals a key insight underlying effective TTRL: metacognitive synergy, where monitoring signals align with the model's optimization regime to enable self-improvement.

cs.LG↗

arXiv2026

Preferred Synthesis of Armchair Transition Metal Dichalcogenide Nanotubes

In this work, we present the synthesis of transition-metal dichalcogenide (TMDC) nanotubes with a preferred chiral angle. SnS2, MoS2, and WS2 are formed with high yield and structural purity inside the channels of boron nitride nanotubes. Atomic-resolution imaging, nano-area electron diffraction, and Circular Dichroism spectroscopy reveal that these synthesized TMDC nanotubes prefer to have an armchair configuration, with a probability up to 84%. Density functional theory reveals a negligible difference in the formation energy between armchair and zigzag nanotubes, suggesting that the chirality preference does not originate from the differences in structural stability. However, a detailed TEM investigation revealed that these TMDC nanotubes formed via a transition state of nanoribbons, and these nanoribbons are energetically more stable in a zigzag configuration. Subsequent machine learning potential molecular dynamics simulations verify that zigzag nanoribbons do roll up to form an armchair SnS2 nanotubes. Finally, this "zigzag nanoribbon to armchair nanotube" transition process is directly observed in real time by in-situ transmission electron microscopy. This work demonstrates the first, but likely general, experimental strategy for synthesizing chirality-preferred TMDC nanotubes.

cond-mat.mtrl-sci↗

arXiv2026

EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation

The development of unified multimodal large language models (MLLMs) is fundamentally challenged by the granularity gap between visual understanding and generation: understanding requires high-level semantic abstractions, while image generation demands fine-grained pixel-level representations. Existing approaches usually enforce the two supervision on the same set of representation or decouple these two supervision on separate feature spaces, leading to interference and inconsistency, respectively. In this work, we propose EvoTok, a unified image tokenizer that reconciles these requirements through a residual evolution process within a shared latent space. Instead of maintaining separate token spaces for pixels and semantics, EvoTok encodes an image into a cascaded sequence of residual tokens via residual vector quantization. This residual sequence forms an evolution trajectory where earlier stages capture low-level details and deeper stages progressively transition toward high-level semantic representations. Despite being trained on a relatively modest dataset of 13M images, far smaller than the billion-scale datasets used by many previous unified tokenizers, EvoTok achieves a strong reconstruction quality of 0.43 rFID on ImageNet-1K at 256x256 resolution. When integrated with a large language model, EvoTok shows promising performance across 7 out of 9 visual understanding benchmarks, and remarkable results on image generation benchmarks such as GenEval and GenAI-Bench. These results demonstrate that modeling visual representations as an evolving trajectory provides an effective and principled solution for unifying visual understanding and generation.

cs.CV↗

arXiv2026

UniWeTok: An Unified Binary Tokenizer with Codebook Size $\mathit{2^{128}}$ for Unified Multimodal Large Language Model

Unified Multimodal Large Language Models (MLLMs) require a visual representation that simultaneously supports high-fidelity reconstruction, complex semantic extraction, and generative suitability. However, existing visual tokenizers typically struggle to satisfy these conflicting objectives within a single framework. In this paper, we introduce UniWeTok, a unified discrete tokenizer designed to bridge this gap using a massive binary codebook ($\mathit{2^{128}}$). For training framework, we introduce Pre-Post Distillation and a Generative-Aware Prior to enhance the semantic extraction and generative prior of the discrete tokens. In terms of model architecture, we propose a convolution-attention hybrid architecture with the SigLu activation function. SigLu activation not only bounds the encoder output and stabilizes the semantic distillation process but also effectively addresses the optimization conflict between token entropy loss and commitment loss. We further propose a three-stage training framework designed to enhance UniWeTok's adaptability cross various image resolutions and perception-sensitive scenarios, such as those involving human faces and textual content. On ImageNet, UniWeTok achieves state-of-the-art image generation performance (FID: UniWeTok 1.38 vs. REPA 1.42) while requiring a remarkably low training compute (Training Tokens: UniWeTok 33B vs. REPA 262B). On general-domain, UniWeTok demonstrates highly competitive capabilities across a broad range of tasks, including multimodal understanding, image generation (DPG Score: UniWeTok 86.63 vs. FLUX.1 [Dev] 83.84), and editing (GEdit Overall Score: UniWeTok 5.09 vs. OmniGen 5.06). We release code and models to facilitate community exploration of unified tokenizer and MLLM.

cs.CV↗

arXiv2026

VirtueBench: Evaluating Trustworthiness under Uncertainty in Long Video Understanding

Recent Vision-Language Models (VLMs) have made remarkable progress in multimodal understanding tasks, yet their evaluation on long video understanding remains unreliable. Due to limited frame inputs, key frames necessary for answering the question may be missing from the model's input. However, models that truthfully refuse to answer under such uncertainty are marked as incorrect, while those that guess may coincidentally produce the correct answer and thus obtain deceptively higher accuracy, leading to misleading evaluation results and encouraging models to guess rather than respond honestly. To address this issue, we introduce VirtueBench, a benchmark explicitly designed to assess model trustworthiness under uncertainty. VirtueBench constructs multiple frame-sampling levels for each video and provides ground truths that distinguish between answerable and unanswerable cases. Evaluations on 25 open-source and commercial VLMs reveal distinct refusal behaviors across different model families, with refusal accuracy ranging from over 70% in the best models to nearly 0% in the worst. Moreover, most models exhibit a substantial drop in refusal when the prompt does not explicitly require them to do so. These findings highlight the need for developing trustworthy VLMs for multimodal understanding, guided by benchmarks and leaderboards that emphasize reliability and trustworthiness.

cs.CV↗

arXiv2026

Ground States of Attractive Fermi Schrödinger Systems with Ring-Shaped Potentials

As an application of the finite-rank Lieb-Thirring inequality established in [R. L. Frank, D. Gontier and M. Lewin, Comm. Math. Phys., 2021], we study ground states of mass-critical N-coupled Fermi nonlinear Schrödinger systems with attractive interactions in $\mathbb{R}^3$, which are trapped in ring-shaped potentials. For any given $N\in\mathbb{N}^+$, we prove that ground states exist if $0<a<a_N^*$, where $a$ denotes the strength of attractive interactions in the system, and $a_N^*$ is the best constant of a finite-rank Lieb-Thirring inequality. Moreover, for some $N\in\mathbb{N}^+$, we also prove the nonexistence of minimizers for the system as soon as $a\geq a_N^*$. Applying the energy estimates and the blow-up analysis, we further analyze the mass concentration behavior of ground states for the system as $a\nearrow a_N^*$.

math.AP↗

arXiv2026

From Physician Expertise to Clinical Agents: Preserving, Standardizing, and Scaling Physicians' Medical Expertise with Lightweight LLM

Medicine is an empirical discipline refined through long-term observation and the messy, high-variance reality of clinical practice. Physicians build diagnostic and therapeutic competence through repeated cycles of application, reflection, and improvement, forming individualized methodologies. Yet outcomes vary widely, and master physicians' knowledge systems are slow to develop and hard to transmit at scale, contributing to the scarcity of high-quality clinical expertise. To address this, we propose Med-Shicheng, a general framework that enables large language models to systematically learn and transfer distinguished physicians' diagnostic-and-therapeutic philosophy and case-dependent adaptation rules in a standardized way. Built on Tianyi, Med-Shicheng consists of five stages. We target five National Masters of Chinese Medicine or distinguished TCM physicians, curate multi-source materials, and train a single model to internalize all five knowledge systems across seven tasks, including etiology-pathogenesis analysis, syndrome diagnosis, treatment principle selection, prescription generation, prescription explanation, symptom evolution with regimen adjustment, and clinical advice. Implemented on Qwen2.5-1.5B-Base, Med-Shicheng runs on resource-constrained GPUs while achieving performance comparable to DeepSeek-R1 and GPT-5. We also examine the reliability of LLM-as-a-judge versus physician evaluation: automated judging tracks overall trends but shows bias on fine-grained individualized distinctions, highlighting the need for physician involvement when ground truth is unavailable and for domain-adapted judge models.

cs.CL↗

arXiv2026

EvoTool: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection

LLM-based agents depend on effective tool-use policies to solve complex tasks, yet optimizing these policies remains challenging due to delayed supervision and the difficulty of credit assignment in long-horizon trajectories. Existing optimization approaches tend to be either monolithic, which are prone to entangling behaviors, or single-aspect, which ignore cross-module error propagation. To address these limitations, we propose EvoTool, a self-evolving framework that optimizes a modular tool-use policy via a gradient-free evolutionary paradigm. EvoTool decomposes agent's tool-use policy into four modules, including Planner, Selector, Caller, and Synthesizer, and iteratively improves them in a self-improving loop through three novel mechanisms. Trajectory-Grounded Blame Attribution uses diagnostic traces to localize failures to a specific module. Feedback-Guided Targeted Mutation then edits only that module via natural-language critique. Diversity-Aware Population Selection preserves complementary candidates to ensure solution diversity. Across four benchmarks, EvoTool outperforms strong baselines by over 5 points on both GPT-4.1 and Qwen3-8B, while achieving superior efficiency and transferability. The code will be released once paper is accepted.

cs.AI↗

arXiv2026

A robust and powerful method for assessing replicability of high dimensional data

Identifying signals that replicate across multiple studies is essential for establishing robust scientific evidence, yet existing methods for high-dimensional replicability analysis either rely on restrictive modeling assumptions, are limited to two-study settings, or lack statistical power. We propose a general empirical Bayes framework for multi-study replicability analysis that jointly models summary-level $p$-values while explicitly accounting for between-study heterogeneity. Within each study, non-null $p$-value densities are estimated nonparametrically under monotonicity constraints, enabling flexible and tuning-free inference. For two studies, we develop a local false discovery rate (Lfdr) statistic for the composite null of non-replicability and establish identifiability, consistency, and a cubic-rate convergence of the nonparametric MLE, along with minimax optimality. Extending replicability analysis to $n$ studies typically requires estimating $2^n$ latent configurations, which is computationally infeasible. To address this challenge, we introduce a scalable pairwise rejection strategy that decomposes the exponentially large composite null into disjoint components, yielding linear complexity in the number of studies. We prove asymptotic FDR control under mild regularity conditions and show that Lfdr-based thresholding is power-optimal. Extensive simulations demonstrate that our method provides substantial power gains while maintaining valid FDR control, outperforming state-of-the-art alternatives across a wide range of scenarios. Applying our framework to East Asian- and European-ancestry genome-wide association studies of type 2 diabetes reveals replicable genetic associations that competing approaches fail to detect, illustrating the method's practical utility in large-scale biomedical research.

stat.ME↗

arXiv2026

Multi-view Attention Fusion of Heterogeneous Hypergraph with Dynamic Behavioral Profiling for Personalized Learning Resource Recommendation

Hypergraph can capture complex and higher-order dependencies among learners and learning resources in personalized educational recommender systems. Many existing hypergraph-based recommendation approaches underexplored the dynamic behavioral processes inherent to learning and often oversimplified the complementary information embedded across multiple dimensions (i.e. views) within hypergraphs. These limitations compromise both the distinctiveness of learned representations and the model's generalization capabilities, especially under data-sparse conditions typical in educational settings. In this study, we propose a unified model comprising a dynamic behavioral profiling module and a multi-view attention fusion module based on heterogeneous hypergraph construction. The dynamic behavioral profiling module is designed to capture evolving behavioral processes and infer latent higher-order relations crucial for hypergraph completion; The multi-view fusion module cohesively integrates information from distinct relational views, enriching the overall data representation. The proposed model was systematically evaluated on five public benchmark datasets and one real-world, self-constructed dataset. Experimental results demonstrate that the model outperforms baseline methods across most datasets in key metrics; Furthermore, hypergraph completion based on dynamic behavioral profiling contributes significantly to performance gains, though its efficacy is modulated by dataset characteristics. Beyond offline experiments, we implemented a functional prototype system tailored for postgraduate student literature recommendation. A mixed-methods user study was conducted to assess its practical utility. Quantitative analysis revealed significantly higher perceived recommendation quality; Qualitative feedback highlighted enhanced user engagement and satisfaction with the prototype system.

cs.IR↗

arXiv2026

ShipTraj-R1: Reinforcing Ship Trajectory Prediction in Large Language Models via Group Relative Policy Optimization

Recent advancements in reinforcement fine-tuning have significantly improved the reasoning ability of large language models (LLMs). In particular, methods such as group relative policy optimization (GRPO) have demonstrated strong capabilities across various fields. However, applying LLMs to ship trajectory prediction remains largely unexplored. In this paper, we propose ShipTraj-R1, a novel LLM-based framework that reformulates ship trajectory prediction as a text-to-text generation problem. (1) We design a dynamic prompt containing trajectory information about conflicting ships to guide the model to achieve adaptive chain-of-thought (CoT) reasoning. (2) We introduce a comprehensive rule-based reward mechanism to incentivize the reasoning format and prediction accuracy of the model. (3) Our ShipTraj-R1 is reinforced through the GRPO mechanism guided by domain-specific prompts and rewards, and utilizes the Qwen3 as the model backbone. Extensive experimental results on two complex and real-world maritime datasets show that the proposed ShipTraj-R1 achieves the least error compared with state-of-the-art deep learning and LLM-based baselines.

cs.AI↗

arXiv2026

Semantic Parallelism: Redefining Efficient MoE Inference via Model-Data Co-Scheduling

Prevailing LLM serving engines employ expert parallelism (EP) to implement multi-device inference of massive MoE models. However, the efficiency of expert parallel inference is largely bounded by inter-device communication, as EP embraces expensive all-to-all collectives to route tokens to the remote experts if not collocating on the same GPU/NPU device. Nevertheless, state-of-the-art schemes treat expert device-placement and request (or token) device-scheduling as separate concerns, triggering excessive communication between them and compromising inference efficiency This paper proposes Semantic Parallelism, a novel parallelism paradigm that minimizes the steep communication costs in EP-centric MoE serving via model-data collaborative scheduling. We implement Semantic Parallelism in a framework called Sem-MoE. Sem-MoE maximally collocates experts and their activating tokens onto the same device using proactively modeled activation likelihood between them and introduces three key techniques: (1) Offline model scheduling, which preliminarily clusters and collocates experts onto devices based on their co-activation tendencies for certain classes of input. (2) Online inter-request data scheduling for Attention-DP setups, which proactively rebatches incoming requests onto the device that hosts experts most likely and frequently activated by the corresponding requests. (3) Online intra-request data scheduling for Attention-TP setups, which seamlessly fuses a token reshuffling procedure into the original inference pipeline and proactively reschedules tokens to devices to reduce dispersed remote routing. We build Sem-MoE into a prevailing LLM serving engine SGLANG. Experiments show our collaborative scheduling approach can effectively reduce the all-to-all communication volume in EP and achieve superior inference throughput compared to existing solutions.

cs.LG↗

arXiv2026

Should Bias be Eliminated? A General Framework to Use Bias for OOD Generalization

Most approaches to out-of-distribution (OOD) generalization learn domain-invariant representations by discarding contextual bias. In this paper, we raise a critical question: Should bias be eliminated? If not, is there a general way to leverage bias for better OOD generalization? To answer these questions, we first provide a theoretical analysis that characterizes the circumstances in which biased features contribute positively. Although theoretical results show that bias may sometimes play a positive role, leveraging it effectively is non-trivial, since its harmful and beneficial components are often entangled. Recent advances have sought to refine the prediction of bias by presuming reliable predictions from invariant features. However, such assumptions may be too strong in the real world, especially when the target also shifts from training to testing domains. Motivated by this challenge, we introduce a framework to leverage bias in a more general scenario. Specifically, we employ a generative model to capture the data generation process and identify the underlying bias factors, which are then used to construct a bias-aware predictor. Since the bias-aware predictor may shift across environments, we first estimate the environment state to train predictors under different environments, combining them as a mixture of domain experts for the final prediction. Then, we build a general invariant predictor, which can be invariant under label shift to guide the adaptation of the bias-aware predictor. Evaluations on synthetic data and standard domain generalization benchmarks demonstrate that our method consistently outperforms both invariance only baselines, recent bias utilization approaches and advanced baselines, yielding improved robustness and adaptability.

cs.LG↗

arXiv2026

Structures of iron and cobalt bimetallic clusters for optimized chemical vapor deposition growth of single-walled carbon nanotubes

We investigate iron-cobalt (Fe-Co) alloys as a representative high-performance catalyst system for SWCNT growth in a systematic manner by combining chemical vapor deposition (CVD) experiments with chirality-resolved spectroscopic analysis, as well as molecular dynamics (MD) simulations based on density functional theory-derived machine learning force fields while varying the Fe-Co ratio. Using zeolite-based SWCNTs prepared by alcohol CVD, absorption and photoluminescence spectroscopy, together with two-dimensional excitation-emission fitting was employed to quantify chirality-specific growth efficiency. Two distinct growth regimes were identified. At a relatively low temperature of 600 C, pure Co exhibits the highest catalytic activity, promoting efficient growth of small-diameter (0.7-0.9 nm) SWCNTs. In contrast, at 850 C, the Fe0.75Co0.25 alloy shows a pronounced enhancement in growth efficiency compared with pure Fe, pure Co, and other Fe-Co compositions, also yielding larger diameter tubes (0.9-1.1nm). Similar growth behavior was observed on SiO2 substrates, enabling detailed transmission electron microscopy analysis of catalyst nanoparticles. Electron microscopy and energy-dispersive X-ray spectroscopy reveal that high SWCNT yields correlate with the formation of small, uniform Fe-Co nanoparticles with Co-enriched surfaces, in excellent agreement with MD simulations. Lastly, MD results are summarized in a composition-diameter phase diagram that rationalizes the experimentally observed growth trends. The exceptional performance of the Fe0.75Co0.25 catalyst at high temperature is attributed to the stabilization of small and uniform catalyst clusters, providing mechanistic insight into the synergistic roles of alloy composition and temperature in SWCNT growth.

cond-mat.mtrl-sci↗

arXiv2026

StomataSeg: Semi-Supervised Instance Segmentation for Sorghum Stomatal Components

Sorghum is a globally important cereal grown widely in water-limited and stress-prone regions. Its strong drought tolerance makes it a priority crop for climate-resilient agriculture. Improving water-use efficiency in sorghum requires precise characterisation of stomatal traits, as stomata control of gas exchange, transpiration and photosynthesis have a major influence on crop performance. Automated analysis of sorghum stomata is difficult because the stomata are small (often less than 40 $μ$m in length in grasses such as sorghum) and vary in shape across genotypes and leaf surfaces. Automated segmentation contributes to high-throughput stomatal phenotyping, yet current methods still face challenges related to nested small structures and annotation bottlenecks. In this paper, we propose a semi-supervised instance segmentation framework tailored for analysis of sorghum stomatal components. We collect and annotate a sorghum leaf imagery dataset containing 11,060 human-annotated patches, covering the three stomatal components (pore, guard cell and complex area) across multiple genotypes and leaf surfaces. To improve the detection of tiny structures, we split high-resolution microscopy images into overlapping small patches. We then apply a pseudo-labelling strategy to unannotated images, producing an additional 56,428 pseudo-labelled patches. Benchmarking across semantic and instance segmentation models shows substantial performance gains: for semantic models the top mIoU increases from 65.93% to 70.35%, whereas for instance models the top AP rises from 28.30% to 46.10%. These results demonstrate that combining patch-based preprocessing with semi-supervised learning significantly improves the segmentation of fine stomatal structures. The proposed framework supports scalable extraction of stomatal traits and facilitates broader adoption of AI-driven phenotyping in crop science.

cs.CV↗

arXiv2026

Robust Transceiver Design for RIS Enhanced Dual-Functional Radar-Communication with Movable Antenna

Movable antennas (MAs) have demonstrated significant potential in enhancing the performance of dual-functional radar-communication (DFRC) systems. In this paper, we explore an MA-aided DFRC system that utilizes a reconfigurable intelligent surface (RIS) to enhance signal coverage for communications in dead zones. To enhance the radar sensing performance in practical DFRC environments, we propose a unified robust transceiver design framework aimed at maximizing the minimum radar signal-to-interference-plus-noise ratio (SINR) in a cluttered environment. Our approach jointly optimizes transmit beamforming, receive filtering, antenna placement, and RIS reflecting coefficients under imperfect channel state information (CSI) for both sensing and communication channels. To deal with the channel uncertainty-constrained issue, we leverage the convex hull method to transform the primal problem into a more tractable form. We then introduce a two-layer block coordinate descent (BCD) algorithm, incorporating fractional programming (FP), successive convex approximation (SCA), S-Lemma, and penalty techniques to reformulate it into a series of semidefinite program (SDP) subproblems that can be efficiently solved. We provide a comprehensive analysis of the convergence and computational complexity for the proposed design framework. Simulation results demonstrate the robustness of the proposed method, and show that the MA-based design framework can significantly enhance the radar SINR performance while achieving an effective balance between the radar and communication performance.

eess.SP↗

arXiv2026

A Collaborative Extended Reality Prototype for 3D Surgical Planning and Visualization

We present a collaborative extended reality (XR) prototype for 3D surgical planning and visualization. Our system consists of three key modules: XR-based immersive surgical planning, cloud-based data management, and coordinated stereoscopic 3D displays for interactive visualization. We describe the overall workflow, core functionalities, implementations and setups. By conducting user studies on a liver resection surgical planning case, we demonstrate the effectiveness of our prototype and provide practical insights to inspire future advances in medical XR collaboration.

cs.HC↗

arXiv2026

Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation

In recent years, aerial object detection has been increasingly pivotal in various earth observation applications. However, current algorithms are limited to detecting a set of pre-defined object categories, demanding sufficient annotated training samples, and fail to detect novel object categories. In this paper, we put forth a novel formulation of the aerial object detection problem, namely open-vocabulary aerial object detection (OVAD), which can detect objects beyond training categories without costly collecting new labeled data. We propose CastDet, a CLIP-activated student-teacher detection framework that serves as the first OVAD detector specifically designed for the challenging aerial scenario, where objects often exhibit weak appearance features and arbitrary orientations. Our framework integrates a robust localization teacher along with several box selection strategies to generate high-quality proposals for novel objects. Additionally, the RemoteCLIP model is adopted as an omniscient teacher, which provides rich knowledge to enhance classification capabilities for novel categories. A dynamic label queue is devised to maintain high-quality pseudo-labels during training. By doing so, the proposed CastDet boosts not only novel object proposals but also classification. Furthermore, we extend our approach from horizontal OVAD to oriented OVAD with tailored algorithm designs to effectively manage bounding box representation and pseudo-label generation. Extensive experiments for both tasks on multiple existing aerial object detection datasets demonstrate the effectiveness of our approach. The code is available at https://github.com/VisionXLab/CastDet.

cs.CV↗