arXiv subjects

Lan Yu

Publications and source records attributed to Lan Yu.

15 recordsLinked to original sources

arXiv2026

Unified Multiparadigm Fusion Intelligence for Rare Disease Diagnosis

Rare diseases (RDs) affect an estimated 300 million people globally, leaving patients to navigate a protracted diagnostic odyssey constrained by clinical scarcity and fragmented medical knowledge. Artificial intelligence (AI) has progressively advanced RD diagnostics, from symbolic methods and deep learning to large language model (LLM)-based systems. However, each paradigm carries structural limitations: symbolic methods are bounded by knowledge completeness, neural models sacrifice interpretability, and LLM-based systems are vulnerable to evaluation biases like data leakage. In this study, we introduce FusionRare, a unified multiparadigm fusion framework integrating knowledge-driven symbolic reasoning, deep-learning pattern recognition, case-based patient retrieval, and LLM-based heuristic inference via statistical meta-aggregation and knowledge-enhanced agentic reflection. Evaluated on 2,528 strictly isolated clinical cases, FusionRare achieves state-of-the-art RD prioritization, attaining a macro-averaged Recall @1 of 51% for phenotype-only diagnosis and 79% for phenotype-genotype joint analysis. These results represent decisive advantages over the advanced agentic system DeepRare, frontier LLMs including GPT 5.5, and specialized tools like PhenoBrain and LIRICAL under stringent anti-leakage protocols. A randomized, crossover clinician-AI validation demonstrated that FusionRare elevates the true diagnostic rank in 45% of decisions, improves physician confidence in 62%, and reduces time to diagnosis by 21%. These findings indicate that reconciling these orthogonal AI paradigms significantly enhances diagnostic capabilities, bridging the gap between computational benchmarks and actionable clinical reliability. More broadly, this work provides a replicable framework for deploying trustworthy diagnostic AI across complex, high-stakes, and underserved medical domains.

cs.AI↗

arXiv2026

ATM: Why Latent World Models Can Fail to Plan

Latent world models can achieve accurate latent prediction yet still differ substantially in downstream planning performance. We argue that a key source of this discrepancy lies in the structure of action-induced latent transitions. We formalize action-identifiability through Bayes inverse risk, characterizing how much uncertainty about an action remains after observing the transition it induces. Model-predicted transitions can become highly self-decodable while encoding a domain-specific action relationship that fails to transfer to real environment transitions. We characterize this mismatch through cross-domain inverse transfer, instantiated as the Action-Consistency Transfer Matrix (ATM), a $2\times2$ inverse-risk matrix over real and predicted transition domains. Across TwoRoom, PushT, and OGBench-Cube, true-transition action-identifiability tracks downstream planning substantially better than standard prediction loss, while the full ATM reveals highly self-decodable yet cross-domain-inconsistent predicted transitions. Controlled interventions on the two domains further produce distinct transition structures and planning outcomes, supporting this decomposition. The same diagnostics also support lightweight model screening, reaching 98.81\% pairwise ranking accuracy for candidates separated by more than 5\% success.

cs.CV↗

arXiv2026

Effective Does Not Mean Useful: Conditional Functional Substitutability for Redundancy and Scaling in Transformers

Modern neural networks scale predictably, yet the mechanisms behind these regularities remain unclear. Neural redundancy is typically characterized by component importance or representational similarity, both indirect proxies. We view redundancy as an input-conditioned, dynamic relation: intermediate computational states are functionally redundant when they induce similar downstream responses. We introduce Conditional Functional Substitutability (CFS) to directly characterize such functional substitution. CFS exposes functional relations and reduction potential missed by conventional importance- and similarity-based measures. Across modalities and Transformer families, CFS reveals systematic functional reorganization with scale. Controlled scaling further shows that performance gains need not track growth in substitutability, while fixed-capacity models with more independent functional structure perform better, providing a functional account of diminishing returns. Predicted CFS further enables dynamic computation with a better performance--computation trade-off than importance-based component selection, suggesting new directions for redundancy-aware computation and more efficient model scaling.

cs.AI↗

arXiv2026

RoboFoundry: System-as-Policy Evolution for Self-Learning Embodied Agents

A foundation model should not act in isolation as an embodied agent. Yet, existing methods often optimize individual components of the agent stack, such as memory, context, skills, or action interfaces, rather than treating the supporting system itself as a unified policy. Moreover, interaction alone does not yield self-improvement unless execution experience is converted into persistent, validated system changes. We therefore propose RoboFoundry, the first embodied agentic framework that formulates this process as Self-Evolving System-as-Policy. RoboFoundry diagnoses capability gaps in decision-making and memory management, converts execution traces into validated task-specific system updates, and promotes recurring improvements to the general system. Evolution operates over two complementary surfaces: a context system that manages active internal context and persistent file-system memory, and a hierarchical skill system that organizes atomic skills, reusable compositions, and failure-conditioned recovery. A shared semantic interface separates embodiment-invariant decisions from embodiment-specific execution, allowing evolved system capabilities to transfer across heterogeneous robots. On EmbodiedBench, RoboFoundry achieves state-of-the-art performance, notably improving GPT-5.5 by 27.8%. It also brings Qwen3.7-Plus to near parity with GPT-5.5 (70.3% vs. 72.7%), showing consistent gains from system-as-policy evolution across foundation models. For long-horizon memory, RoboFoundry outperforms all baselines on RoboMemArena by at least 39.0%, even against methods assisted by external foundation models. On LIBERO-PRO, it further outperforms Cap-Agent0 by 243.8%-679.7% across all perturbation types. In real-world deployments, RoboFoundry demonstrates zero-shot transfer and online evolution across robots and tasks, highlighting its potential for fully autonomous embodied agents.

cs.RO↗

arXiv2026

Learning from Mixed-Quality Deployment Experience for Robot Manipulation

Robot policies deployed in real environments naturally accumulate mixed-quality experience, including successful executions, partial progress, and failures. Although these rollouts provide valuable information for further learning, directly incorporating them into imitation learning may reinforce undesirable behaviors, while offline reinforcement learning often suffers from unreliable value estimation under sparse rewards and limited data coverage. We consider a practical post-deployment setting where learning relies only on naturally accumulated autonomous rollouts, without additional human corrections or exploratory interaction. To effectively exploit such experience, we propose Predictive Action Chunk Learning (PACL). PACL first learns a predictive chunk-level critic that evaluates temporally extended action sequences and augments temporal difference learning with future latent prediction, providing richer supervision for long-horizon value estimation. The learned critic then converts chunk-level Q-values into discrete quality conditions, which guide a diffusion actor to learn jointly from these mixed-quality experiences without treating all behaviors as equivalent supervision. At inference, the actor generates multiple action chunks and the critic selects the highest valued candidate. Experiments across simulated and real-world robot manipulation tasks show that PACL consistently improves the pretrained policy and outperforms strong imitation learning and offline reinforcement learning baselines.

cs.LG↗

arXiv2026

FIERCE: From Generalist Robot Policies to Fast Specialists via Progress-Failure Feedback

Generalist robot policies offer useful initialization, but refining compact specialists through limited physical interaction requires informative learning feedback. We present FIERCE, a generalist-initialized reinforcement learning framework centered on a unified, task-adaptive progress-failure evaluator. Its architecture shares an observation-language representation between an observed-progress head and an action-conditioned latent predictor whose past and current predictions feed a causal sequence head for task-failure estimation. Joint supervision from progress and preference labels, synchronized commands and observations, and terminal outcomes trains the evaluator; target-task rollouts support adaptation and calibration. Fixed evaluator snapshots provide progress shaping and failure-risk penalties alongside independently verified terminal rewards, while evaluator and policy updates alternate as new experience is collected. Refinement requires neither continued generalist action queries nor a dedicated target-task simulator or manually annotated dense rewards. Only the compact specialist is retained at deployment. The evaluation separates feedback quality, policy-learning efficiency, and deployment cost across simulation and two contact-rich real tasks. Code, model weights, and data-restoration tools are released at https://github.com/ar-mine/FIERCE.

cs.RO↗

arXiv2026

Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod

Scaled-out MoE LLMs and scaled-up SuperPods create new systems challenges for production Model-as-a-Service (MaaS), requiring disaggregation, low-latency communication, and decentralized serving. This report presents xDeepServe, the production serving system behind Huawei Cloud's MaaS offering on CloudMatrix384, a 48-server SuperPod with 384 Ascend 910C chips connected by a high-bandwidth UB fabric and global shared memory. It serves models including DeepSeek, Kimi, GLM, Qwen, and MiniMax, among others. xDeepServe is built around Transformerless, a disaggregated execution architecture that decomposes transformer inference into modular units -- attention, feedforward, and MoE -- and supports disaggregated Prefill-Decode and MoE-Attention deployments. To enable disaggregation, we develop XCCL, a memory-semantic communication layer providing microsecond-level point-to-point and scalable all-to-all primitives, and we extend FlowServe with decentralized DP groups and techniques to mitigate stragglers and synchronization variance. In a peak decoding configuration, xDeepServe reaches 2400 tokens/s per Ascend 910C chip at ~50ms time-per-output-token (TPOT).

cs.DC↗

arXiv2025

Direct Observation of d-Wave Superconducting Gap Symmetry in Pressurized La3Ni2O7-delta Single Crystals

The recent discovery of superconductivity in pressure-stabilized bulk La3Ni2O7-delta, with a critical temperature (Tc) exceeding 77 K, has opened a new frontier in high-temperature superconductivity research beyond cuprates. Yet, the superconducting gap amplitude and symmetry, the key parameters to characterize a superconductor, remain elusive due to the overwhelming challenges of gap studies under high pressure. Here, we introduce in situ directional point-contact spectroscopy conducted under truly hydrostatic pressure, enabling the direct mapping of the superconducting gap in pressurized La3Ni2O7-delta single crystals. Depending on the junction orientation, differential conductance (dI/dV) spectra exhibit distinct V-shaped quasiparticle features and a sharp zero-bias peak, indicating a predominant d-wave-like pairing symmetry. Measurement of the c-axis gap amplitude Delta yields a gap-to-Tc ratio of 2Delta/kBTc = 4.2(5), positioning La3Ni2O7-delta firmly among unconventional, nodal high-Tc superconductors. These findings set stringent constraints on theoretical models for nickelate superconductors and establish a robust spectroscopic approach for understanding superconductors under extreme pressures.

cond-mat.supr-con↗

arXiv2025

An Optimization Algorithm for Multimodal Data Alignment

In the data era, the integration of multiple data types, known as multimodality, has become a key area of interest in the research community. This interest is driven by the goal to develop cutting edge multimodal models capable of serving as adaptable reasoning engines across a wide range of modalities and domains. Despite the fervent development efforts, the challenge of optimally representing different forms of data within a single unified latent space a crucial step for enabling effective multimodal reasoning has not been fully addressed. To bridge this gap, we introduce AlignXpert, an optimization algorithm inspired by Kernel CCA crafted to maximize the similarities between N modalities while imposing some other constraints. This work demonstrates the impact on improving data representation for a variety of reasoning tasks, such as retrieval and classification, underlining the pivotal importance of data representation.

cs.LG↗

arXiv2024

Knowledge-aware Alert Aggregation in Large-scale Cloud Systems: a Hybrid Approach

Due to the scale and complexity of cloud systems, a system failure would trigger an "alert storm", i.e., massive correlated alerts. Although these alerts can be traced back to a few root causes, the overwhelming number makes it infeasible for manual handling. Alert aggregation is thus critical to help engineers concentrate on the root cause and facilitate failure resolution. Existing methods typically utilize semantic similarity-based methods or statistical methods to aggregate alerts. However, semantic similarity-based methods overlook the causal rationale of alerts, while statistical methods can hardly handle infrequent alerts. To tackle these limitations, we introduce leveraging external knowledge, i.e., Standard Operation Procedure (SOP) of alerts as a supplement. We propose COLA, a novel hybrid approach based on correlation mining and LLM (Large Language Model) reasoning for online alert aggregation. The correlation mining module effectively captures the temporal and spatial relations between alerts, measuring their correlations in an efficient manner. Subsequently, only uncertain pairs with low confidence are forwarded to the LLM reasoning module for detailed analysis. This hybrid design harnesses both statistical evidence for frequent alerts and the reasoning capabilities of computationally intensive LLMs, ensuring the overall efficiency of COLA in handling large volumes of alerts in practical scenarios. We evaluate COLA on three datasets collected from the production environment of a large-scale cloud platform. The experimental results show COLA achieves F1-scores from 0.901 to 0.930, outperforming state-of-the-art methods and achieving comparable efficiency. We also share our experience in deploying COLA in our real-world cloud system, Cloud X.

cs.SE↗

arXiv2024

Probing superconducting gap in CeH$_9$ under pressure

The recent discovery of superconductivity in hydrogen-rich compounds has garnered significant experimental and theoretical interest because of the record-setting critical temperatures. As the direct observation of the superconducting (SC) gap in these superhydrides is rare, the underlying mechanism behind its occurrence has yet to be settled down. Here, we report a successful synthesis of the $\textit{P6$_3$}$/$\textit{mmc}$ phase of CeH$_9$ that exhibits the SC transition with SC critical temperature of about 100 K at a pressure of about 100 GPa. The observation of the zero electrical resistance and the critical current demonstrates that the SC phase is realized in Ce-based superhydride. Quasiparticle scattering spectroscopy (QSS) reveals the Andreev reflection at zero bias voltage, a hallmark of superconductivity, in the differential conductance. The obtained SC gap-to-$\textit{T}$$_c$ ratio of 4.36 and temperature dependence of SC gap are consistent with the prediction from the Bardeen-Cooper-Schrieffer theory with a moderate coupling strength. The successful realization of QSS under Megabar conditions is expected to provide a desired route to the study of the mechanism of superconductivity as well as the establishment of the SC phase in superhydride high-$\textit{T}$$_c$ systems.

cond-mat.supr-con↗

arXiv2022

Preferences Single-Peaked on a Tree: Multiwinner Elections and Structural Results

A preference profile is single-peaked on a tree if the candidate set can be equipped with a tree structure so that the preferences of each voter are decreasing from their top candidate along all paths in the tree. This notion was introduced by Demange (1982), and subsequently Trick (1989) described an efficient algorithm for deciding if a given profile is single-peaked on a tree. We study the complexity of multiwinner elections under several variants of the Chamberlin-Courant rule for preferences single-peaked on trees. We show that the egalitarian version of this problem admits a polynomial-time algorithm. For the utilitarian version, we prove that winner determination remains NP-hard, even for the Borda scoring function; however, a winning committee can be found in polynomial time if either the number of leaves or the number of internal vertices of the underlying tree is bounded by a constant. To benefit from these positive results, we need a procedure that can determine whether a given profile is single-peaked on a tree that has additional desirable properties (such as, e.g., a small number of leaves). To address this challenge, we develop a structural approach that enables us to compactly represent all trees with respect to which a given profile is single-peaked. We show how to use this representation to efficiently find the best tree for a given profile for use with our winner determination algorithms: Given a profile, we can efficiently find a tree with the minimum number of leaves, or a tree with the minimum number of internal vertices among trees on which the profile is single-peaked. We also consider several other optimization criteria for trees: for some we obtain polynomial-time algorithms, while for others we show NP-hardness results.

cs.GT↗

arXiv2018

Midterm Periodicity Analysis of the Mount Wilson Magnetic Indices Using the Synchrosqueezing Transform

A novel time--frequency technique, called the synchrosqueezing transform (SST), is used to investigate the midterm periodic variations of magnetic fields on the solar surface. The Magnetic Plage Strength Index (MPSI) and the Mount Wilson Sunspot Index (MWSI), measured daily by the Mount Wilson Observatory between 1970 January 19 and 2012 January 22, are selected. The short-, mid, and longer-term periodicities are represented and decomposed by the SST with hardly any mode mixing. This demonstrates that the SST is a useful time--frequency analysis technique to characterize the periodic modes of helioseismic data. Apart from the fundamental modes of the annual periodicity, $\sim$27 day rotational cycle and $\sim$11 year solar cycle, the SST reveals several midterm periodicities in the two magnetic activity indices, specifically, $\sim$157 day (i.e., Rieger-type periodicity), and $\sim$1.3 and 1.7 years. The periodic modes, with 116.4 and 276.2 day periodicity in the MPSI, with 108.5 and 251.6 day periodicity in the MWSI, and the 157.7 day periodicity in the two indices, are in better accord with those significant periodicities derived from the Rossby waves theoretical model. This study suggests that the modes are caused by the Rossby waves. For the 1.30 and 1.71 year periodicity of the MPSI, and the 1.33 and 1.67 year periodicity of the MWSI, our analysis infers that they are related to those periodicity with the same timescale in the interior of the Sun and in the high atmospheric layers.

astro-ph.SR↗

arXiv2014

Complex-Demand Knapsack Problems and Incentives in AC Power Systems

We consider AC electrical systems where each electrical device has a power demand expressed as a complex number, and there is a limit on the magnitude of total power supply. Motivated by this scenario, we introduce the complex-demand knapsack problem (C-KP), a new variation of the traditional knapsack problem, where each item is associated with a demand as a complex number, rather than a real number often interpreted as weight or size of the item. While keeping the same goal as to maximize the sum of values of the selected items, we put the capacity limit on the magnitude of the sum of satisfied demands. For C-KP, we prove its inapproximability by FPTAS (unless P = NP), as well as presenting a (1/2-epsilon)-approximation algorithm. Furthermore, we investigate the selfish multi-agent setting where each agent is in charge of one item, and an agent may misreport the demand and value of his item for his own interest. We show a simple way to adapt our approximation algorithm to be monotone, which is sufficient for the existence of incentive compatible payments such that no agent has an incentive to misreport. Our results shed insight on the design of multi-agent systems for smart grid.

cs.DS↗

arXiv2013

The Complexity of Fully Proportional Representation for Single-Crossing Electorates

We study the complexity of winner determination in single-crossing elections under two classic fully proportional representation rules---Chamberlin--Courant's rule and Monroe's rule. Winner determination for these rules is known to be NP-hard for unrestricted preferences. We show that for single-crossing preferences this problem admits a polynomial-time algorithm for Chamberlin--Courant's rule, but remains NP-hard for Monroe's rule. Our algorithm for Chamberlin--Courant's rule can be modified to work for elections with bounded single-crossing width. To circumvent the hardness result for Monroe's rule, we consider single-crossing elections that satisfy an additional constraint, namely, ones where each candidate is ranked first by at least one voter (such elections are called narcissistic). For single-crossing narcissistic elections, we provide an efficient algorithm for the egalitarian version of Monroe's rule.

cs.GT↗