arXiv subjects

Xiaoyang Li

Publications and source records attributed to Xiaoyang Li.

At least 19 recordsLinked to original sources

arXiv2026

RFS-UNet: Decoder-Conditioned High-Resolution Skip Recalibration for Bone-Selective DRR Synthesis

Bone-selective synthesis from digitally reconstructed radiographs (DRRs) requires separating skeletal signal from overlying tissue while preserving anatomical detail. U-Net skip connections supply fine encoder features, but their transfer is independent of decoder context. We introduce RFS-UNet, which lets the decoder participate in high-resolution channel recalibration. Pooled encoder and decoder features jointly predict a bounded residual scale, initialized to preserve the original skip transfer. The module operates at the two finest resolutions and integrates directly into the backbone. On a rebuilt patient-unique cohort, RFS improves test PSNR over U-Net-64 by 0.10 dB. A three-seed comparison with encoder-only recalibration supports the contribution of decoder context. RFS also offers a lower-latency alternative to CBAM, with 2.25 times faster inference in matched profiling. Decoder-conditioned reuse thus improves bone-selective synthesis through a compact architectural change.

cs.CV↗

arXiv2026

Evaluator-Dependent Patient-Adaptive ECG Lead-Channel Allocation

The diagnostic value of an ECG channel depends on the model that interprets it. We test whether adaptive acquisition retains its advantage over fixed protocols when that model changes. Two policies developed with a logistic evaluator are frozen and assessed with a masked waveform ResNet1D, using exhaustive, metric-matched fixed comparators. On PTB-XL, replacing the evaluator reverses the mean adaptive advantage in negative log-likelihood and Brier score across the tested budgets, while calibration responds less uniformly. The shift persists with common fixed references and broader training-mask exposure. Training a policy against the stronger evaluator partly recovers the lost advantage. These retrospective exploratory results show that acquisition quality cannot be assessed independently of the downstream evaluator and motivate validating adaptive policies with the model intended for diagnosis.

cs.CV↗

arXiv2026

Branch Geometry and Finite-Radius Sensitivity of Hard-ReLU Training

Outer-learning algorithms use infinitesimal sensitivities to propose finite changes to initialization or training parameters. For hard-ReLU training, the derivative of the finite program and the derivative of its flow limit do not by themselves specify the response at a chosen radius. We characterize the intervening regime in which the perturbation radius is proportional to the GD step. Integer event rounding then survives at leading order: smooth Euler bias shifts each discrete phase, and upstream rounding moves downstream branch boundaries. We derive the crossing indices and a uniform endpoint expansion for finitely many separated transverse events in piecewise-$C^2$ dynamics, away from recursive phase boundaries. In contractive affine regions, an explicit remainder and complete branch verification certify finite candidate comparisons. Scalar phase frequencies and a coupled feedback ablation test the mechanism; frozen nonlinear-network experiments show radius-dependent prediction accuracy, including incomplete branch matches and failed-word tails. Together with local AD and uniform flow consistency, the result identifies sufficient response regimes: differentiating training is a choice of perturbation resolution as well as a choice of derivative.

cs.LG↗

arXiv2026

Exploring the Initial Performance of NB-IoT NTN over GEO: Measurement and Analysis

With the standardization of Non-Terrestrial Networks (NTN) to provide direct satellite connectivity to massive, low-power Internet of Things (IoT) devices, 3GPP IoT-NTN bridges the worlds of cellular and satellite communications. While holding great potential for global connectivity with IoT devices, there exist several concerns about the system performance of IoT-NTN over Geostationary Earth Orbit (GEO), which covers multiple dimensions such as end-to-end delay and energy consumption considering the ultra-long transmission distance from ground IoT terminals to GEO satellite. To answer these concerns, we have conducted the first comprehensive and in depth measurement for NB-IoT NTN over GEO. Based on real NB-IoT NTN testbeds including both Skylo and Tiantong, measurements covering more than six months confirm that the available implementation of NB-IoT NTN remains in the initial stage. Amplified by ultra-long Round-Trip Time (RTT) between ground IoT terminals and GEO satellite, there exists plenty of time and energy consumption during the access process. Interestingly, it also reveals that as an energy-saving mechanism, Power Saving Mode (PSM) fundamentally reshapes NB-IoT NTN traffic into a bursty and access-driven communication pattern and thus has a considerable influence on the end-to-end delay and energy consumption. Finally, we propose corresponding optimization schemes to reduce the delay and energy, which lays a good foundation for the implementation of NB-IoT NTN in the near future.

cs.NI↗

arXiv2026

Leakage-Audited Benchmarking Reveals Limited Evidence for Cross-Subject Auditory-Evoked EEG Vowel Perception Decoding

We tested whether auditory-evoked EEG supports subject-independent five-vowel perception decoding when trial identity, model identity, prediction provenance, and participant-level inference are controlled within a single benchmark. We reconstructed Study 2 event tables from OpenNeuro ds006104 version 1.0.1 and analysed the consonant-vowel pair task. One-to-one marker-stimulus pairing yielded 3,840 independent trials; control-condition selection and artifact rejection retained 1,094 epochs from 16 participants and 61 EEG channels. Thirteen unique implementations were evaluated using leave-one-subject-out testing, with participant metrics reconstructed from 36,102 trial predictions across 33 complete prediction replicas. Random Forest was numerically highest at 21.474% balanced accuracy (95% participant-bootstrap interval, 19.526-23.482%; chance, 20%), but neither its participant-level tests nor any implementation survived correction across the 13-model family. Deep-model performance was close to chance, and several architectures showed substantial seed-dependent variation and low trial-label agreement. An exploratory MDM analysis comprising 9,616 genuine refits across training cohorts of 3-15 participants showed no monotonic performance gain. Within this dataset and protocol, evidence for reliable cross-subject five-vowel decoding is limited. The benchmark provides a reproducible chain from source rows to retained epochs, predictions, participant-level metrics, multiplicity-adjusted inference, and bounded diagnostic analyses.

eess.SP↗

arXiv2026

When Do Task Vectors Interfere? Mapping the Validity Boundaries of Weight-Space Composition

Task arithmetic composes skills by adding weight displacements, and merged models are then judged on benchmark suites. We measure when that composition is functionally additive, and find that the answer depends as much on how the model is prompted as on which tasks are merged. Across two-dimensional composition surfaces -- five model settings from 0.5B to 8B, two families, LoRA and full fine-tuning -- pairwise non-additivity is real, seed-stable, and transfers in coarse order to unseen task pairs: all eight preregistered sign predictions held. But it is input-conditioned everywhere we measured: the same merged model that shows a six-point interaction contrast on code prompts shows none on math prompts, and wrapping the identical code prompts in the instruction template the adapters were trained on collapses the contrast twenty-fold, from +6.9 to +0.3 points -- while re-serializing them in an untrained chat template leaves it intact (+12.5), falsifying our own preregistered prediction. Execution benchmarks (pass@1) inherit the training-format wrapper's blindness. Weight-space composition therefore supports coarse, input- and format-conditioned functional statements -- not a universal merging-performance predictor, and not one that training-format evaluations can see.

cs.LG↗

arXiv2026

SenWorld: A Digital-Twin Simulation for Generating Context-Rich Evaluation Data

Smartphone personal assistants reason over longitudinal personal data, yet evaluating them requires context-rich evaluation data whose correct answers are known, and real device traces are too privacy-sensitive to share. To address this challenge, we present SenWorld, a physically grounded, deterministic, event-sourced digital-twin simulation that generates such data with ground truth fixed by construction. In SenWorld, personas live through a full day in a world built from real map, weather, holiday, and network data; every observable signal is archived in full-system snapshots; and each evaluation case is labeled by a pointer to an existing record rather than by post-hoc annotation or a large language model (LLM) judge. We evaluate this method with 16 personas in Beijing. The generated data closely matches the held-out real-user benchmark in category distribution (Jensen--Shannon divergence (JSD) 0.070) and in the daily rhythm of communication records (JSD below 0.1), though generated records remain shorter than real ones. Without scripted interaction, personas form a fully reciprocated dialogue subgraph and differentiated behavioral repertoires. Projected into 717 evaluation cases, the generated data exposes 78 failures in a production smartphone assistant, concentrating on call and Short Message Service (SMS) records while contacts, schedules, and alarms never fail. The snapshot pointer confirms each failure as an assistant-side retrieval error, with no LLM judge involved. Overall, SenWorld offers a privacy-safe, reproducible, and distribution-checked path to evaluation data whose labels are fixed by construction.

cs.AI↗

arXiv2026

MemTX: Transactional Belief Commit for Stateful Agent Memory

LLM agents increasingly coordinate through persistent shared memory: one agent's write becomes another agent's premise, and eventually a tool call with real side effects. Current agent memory systems treat every accepted write as immediately actionable truth, so a polluted tool result, a stale update, or a teammate's half-finished note can silently drive an irreversible action. We argue that a memory write is not a belief commit. We present MemTX, a transactional belief-commit protocol. Each record carries evidence, permissions, provenance, and validity. Writes are staged inside snapshot-isolated transactions and admitted by a validate-and-commit pipeline, irreversible tool calls are gated on in-flight belief state, and retracting a belief triggers typed cascading repair of its derived records and tool side effects. Two invariants, action-safety gating and cascade-repair completeness, are machine-checked by property-based testing and bounded exhaustive enumeration of 5.5 million protocol states, with zero violations. Across five backbones from three model families, MemTX leads all eight baselines with paired-McNemar significance on four backbones and statistically ties the best baseline on the fifth and strongest, while remaining the only method with zero downstream harm on every backbone. Backbone capability does not substitute for commit discipline.

cs.AI↗

arXiv2026

AgentOmnia: Scaling Agentic Models for Full-Scenario Applications

Large language model agents have advanced rapidly, yet progress remains fragmented across domains, capabilities, task difficulty, and interaction settings. We frame this as full-scenario agentic scaling and present AgentOmnia, a framework coordinating task-space definition, data synthesis, post-training, evaluation, and improvement across To-Consumer (ToC), To-Business (ToB), and To-Employee (ToE) applications. An extensible Domain x Capability x Atomic Difficulty taxonomy aligns these stages and enables fine-grained diagnosis with OmniaBench. AgentOmnia combines bidirectional environment-task synthesis with tool-dependency, program-structured, and solver-based pipelines, constructing 5,018 stateful environments with 255,375 tools and 52,361 tasks. Programs, solvers, and verifiers provide correctness signals, while supervised fine-tuning, online agentic reinforcement learning, and a rollback curriculum support post-training. Evaluation failures translate into Product Requirement Documents (PRDs) for targeted self-evolution. Starting from Qwen3-30B-A3B-Thinking-2507, AgentOmnia raises the pass rate on the OmniaBench challenging subset from 9.16% to 37.11% and the macro-average across OmniaBench, $τ^2$-Bench, DeepPlanning, and VitaBench from 22.86% to 41.69%. Under a unified protocol,it leads the evaluated agentic post-trained baselines on OmniaBench and retains the highest four-benchmark macro-average. It also surpasses Qwen3-235B-A22B-Thinking-2507 on all four benchmarks and exceeds Qwen3.5-35B-A3B on the macro-average. Gains span three application splits, ten capability dimensions, eight atomic-difficulty factors, and 76 of 90 level-1 domains, indicating broad rather than category-specific improvement. A one-round study provides initial evidence for PRD-guided self-evolution, motivating validation at larger scales and in industrial settings.

cs.AI↗

arXiv2026

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Reinforcement learning (RL) has gained growing attention in large language model (LLM) post-training, yet RL training remains fragile and can suffer from instability or collapse. One vital cause is training-inference mismatch: LLM adopts separate inference and training engines for generation efficiency and training precision, which in practice exhibits inconsistent probabilities for the same trajectories on training and inference sides, even with synchronized model parameters. This naturally induces a special type of off-policyness ever existing and poisoning the training. Prior works have made various efforts in addressing the off-policyness to stabilize the training policies under the mismatch. In this paper, we point out the objective misalignment neglected by existing works that an effective update to the policy in the training engine not necessarily ensures the improvement of the inference policy, i.e., the one used in deployment. To this end, we propose a new policy optimization objective for LLM RL, named Monotonic Inference Policy Improvement (MIPI). Following this principle, we introduce Monotonic Inference Policy Update (MIPU), a two-step LLM RL framework that constructs sampler-referenced candidate updates and selectively accepts synchronized candidates using an inference-side gap proxy. Experiments conducted on two model scales under high mismatch show that MIPU improves average reasoning performance and training stability.

cs.LG↗

arXiv2026

Performance Analysis for Heterogeneous Air-Ground ISAC in Coordinated Multipoint Networks

The emergence of the \textit{low-altitude economy} (LAE) calls for highly integrated and reliable wireless systems that can simultaneously support \textit{communication and sensing} (C\&S) functions. Although \textit{integrated sensing and communication} (ISAC) has been widely studied, most existing works focused on link-level or single-cell architectures in terrestrial environments, leaving the potential of network-level cooperative air-ground ISAC largely unexplored. To bridge this gap, a heterogeneous air-ground ISAC network architecture based on \textit{coordinated multipoint} (CoMP) is proposed, which incorporates a cooperative hybrid mono/bi-static sensing scheme to enhance spatial diversity and sensing capability. In the proposed architecture, a two-tier \textit{base station} (BS) deployment is adopted: master BSs are arranged in a hexagonal lattice, while slave BSs follow a Poisson point process distribution. This structure concurrently supports communication for terrestrial users and sensing for aerial targets. A holistic performance analysis framework for both C\&S is further developed, accounting for key channel and network parameters. Simulation results reveal inherent trade-offs between C\&S performance, especially under multi-BS cooperation and varying network density. These findings provide practical guidance for the deployment of scalable and efficient ISAC networks in LAE scenarios.

cs.IT↗

arXiv2026

A Stochastic Hybrid Automaton for Smartphone Battery Dynamics: Electro-Thermal Coupling and First-Passage Time-to-Empty Estimation

Smartphone time-to-empty (TTE) is difficult to predict because shutdown is governed not only by remaining charge, but also by instantaneous power capability under temperature-, aging-, and load-dependent voltage sag. We develop a stochastic hybrid automaton for smartphone battery dynamics that couples a first-order Thevenin equivalent-circuit model with a lumped thermal model and a stochastic user-activity process. The continuous state includes state of charge, polarization voltage, and battery temperature; user behavior is represented as a piecewise deterministic Markov process switching among idle, social/web, video, gaming, and weak-signal modes. Shutdown is formulated as a first-passage event when terminal voltage crosses a cutoff threshold or when requested power exceeds the instantaneous feasibility envelope. The model captures a voltage-collapse mechanism that simple Coulomb-counting or linear discharge models miss: cold temperature or battery aging increases internal resistance, so high-power bursts can drive terminal voltage below cutoff even when substantial charge remains. Monte Carlo simulation yields a full TTE distribution rather than a single countdown, allowing lower-tail risk to be quantified by the 5th percentile. Sensitivity analysis identifies ambient temperature, internal resistance, weak-signal radio penalty, and screen brightness as major drivers of premature shutdown risk. These results motivate practical user guidance and an operating-system-level resistance-aware throttling policy that limits peak power in the power-limited regime. The framework provides a physically grounded, risk-aware approach for explaining and extending usable smartphone battery life under real-world uncertainty.

eess.SY↗

arXiv2026

AdaGamma: State-Dependent Discounting for Temporal Adaptation in Reinforcement Learning

The discount factor in reinforcement learning controls both the effective planning horizon and the strength of bootstrapping, yet most deep RL methods use a single fixed value across all states. While state-dependent discounting is conceptually appealing, naive deep actor--critic implementations can become unstable and degenerate toward TD-error collapse. We propose AdaGamma, a practical deep actor--critic method for state-dependent discounting that learns a state-dependent discount function together with a return-consistency objective to regularize the induced backup structure. On the theory side, we analyze the Bellman operator induced by state-dependent discounting and establish its basic well-posedness properties under suitable conditions. Empirically, AdaGamma integrates into both SAC and PPO, yielding consistent improvements on continuous-control benchmarks, and achieves statistically significant gains in an online A/B test on the JD Logistics platform. These results suggest that state-dependent discounting can be made effective in deep RL when coupled with a return-consistency objective that prevents degenerate target manipulation.

cs.LG↗

arXiv2026

Opportunistic Bone-Loss Screening from Routine Knee Radiographs Using a Multi-Task Deep Learning Framework with Sensitivity-Constrained Threshold Optimization

Background: Osteoporosis and osteopenia are often undiagnosed until fragility fractures occur. Dual-energy X-ray absorptiometry (DXA) is the reference standard for bone mineral density (BMD) assessment, but access remains limited. Knee radiographs are obtained at high volume for osteoarthritis evaluation and may offer an opportunity for opportunistic bone-loss screening. Objective: To develop and evaluate a multi-task deep learning system for opportunistic bone-loss screening from routine knee radiographs without additional imaging or patient visits. Methods: We developed STR-Net, a multi-task framework for single-channel grayscale knee radiographs. The model includes a shared backbone, global average pooling feature aggregation, a shared neck, and a task-aware representation routing module connected to three task-specific heads: binary screening (Normal vs. Bone Loss), severity sub-classification (Osteopenia vs. Osteoporosis), and weakly coupled T-score regression with optional clinical variables. A sensitivity-constrained threshold optimization strategy (minimum sensitivity >= 0.86) was applied. The dataset included 1,570 knee radiographs, split at the patient level into training (n=1,120), validation (n=226), and test (n=224) sets. Results: On the held-out test set, STR-Net achieved an AUROC of 0.933, sensitivity of 0.904, specificity of 0.773, and AUPRC of 0.956 for binary screening. Severity sub-classification achieved an AUROC of 0.898. The T-score regression branch showed a Pearson correlation of 0.801 with DXA-measured T-scores in a pilot subset (n=31), with MAE of 0.279 and RMSE of 0.347. Conclusions: STR-Net enables single-pass bone-loss screening, severity stratification, and quantitative T-score estimation from routine knee radiographs. Prospective clinical validation is needed before deployment.

cs.CV↗

arXiv2026

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal systems remain language-centric, often treating non-linguistic modalities as external attachments, leading to fragmented architectures and suboptimal integration. To transcend this limitation, we introduce Discrete Native Autoregressive (DiNA), a unified framework that represents multimodal information within a shared discrete space, enabling a consistent and principled autoregressive modeling across modalities. A key innovation is the Discrete Native Any-resolution Visual Transformer (dNaViT), which performs tokenization and de-tokenization at arbitrary resolutions, transforming continuous visual signals into hierarchical discrete tokens. Building on this foundation, we develop LongCat-Next, a native multimodal model that processes text, vision, and audio under a single autoregressive objective with minimal modality-specific design. As an industrial-strength foundation model, it excels at seeing, painting, and talking within a single framework, achieving strong performance across a wide range of multimodal benchmarks. In particular, LongCat-Next addresses the long-standing performance ceiling of discrete vision modeling on understanding tasks and provides a unified approach to effectively reconcile the conflict between understanding and generation. As an attempt toward native multimodality, we open-source the LongCat-Next and its tokenizers, hoping to foster further research and development in the community. GitHub: https://github.com/meituan-longcat/LongCat-Next

cs.CV↗

arXiv2026

AGE-Net: Spectral--Spatial Fusion and Anatomical Graph Reasoning with Evidential Ordinal Regression for Knee Osteoarthritis Grading

Automated Kellgren--Lawrence (KL) grading from knee radiographs is challenging due to subtle structural changes, long-range anatomical dependencies, and ambiguity near grade boundaries. We propose AGE-Net, a ConvNeXt-based framework that integrates Spectral--Spatial Fusion (SSF), Anatomical Graph Reasoning (AGR), and Differential Refinement (DFR). To capture predictive uncertainty and preserve label ordinality, AGE-Net employs a Normal-Inverse-Gamma (NIG) evidential regression head and a pairwise ordinal ranking constraint. On a knee KL dataset, AGE-Net achieves a quadratic weighted kappa (QWK) of 0.9017 +/- 0.0045 and a mean squared error (MSE) of 0.2349 +/- 0.0028 over three random seeds, outperforming strong CNN baselines and showing consistent gains in ablation studies. We further outline evaluations of uncertainty quality, robustness, and explainability, with additional experimental figures to be included in the full manuscript.

cs.CV↗

arXiv2026

OrchMLLM: Orchestrate Multimodal Data with Batch Post-Balancing to Accelerate Multimodal Large Language Model Training

Multimodal large language models (MLLMs), such as GPT-4o, are garnering significant attention. During the exploration of MLLM training, we identified Modality Composition Incoherence, a phenomenon that the proportion of a certain modality varies dramatically across different examples. It exacerbates the challenges of addressing mini-batch imbalances, which lead to uneven GPU utilization between Data Parallel (DP) instances and severely degrades the efficiency and scalability of MLLM training, ultimately affecting training speed and hindering further research on MLLMs. To address these challenges, we introduce OrchMLLM, a comprehensive framework designed to mitigate the inefficiencies in MLLM training caused by Modality Composition Incoherence. First, we propose Batch Post-Balancing Dispatcher, a technique that efficiently eliminates mini-batch imbalances in sequential data. Additionally, we integrate MLLM Global Orchestrator into the training framework to orchestrate multimodal data and tackle the issues arising from Modality Composition Incoherence. We evaluate OrchMLLM across various MLLM sizes, demonstrating its efficiency and scalability. Experimental results reveal that OrchMLLM achieves a Model FLOPs Utilization (MFU) of $41.6\%$ when training an 84B MLLM with three modalities on $2560$ H100 GPUs, outperforming Megatron-LM by up to $3.1\times$ in throughput.

cs.DC↗

arXiv2026

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its importance, the open-source community lacks a principled, end-to-end ecosystem to streamline agent development. We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimizes the production pipeline for agentic model. ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering. We release ROME, an open-source agent grounded by ALE and trained on over one million trajectories. Our approach includes data composition protocols for synthesizing complex behaviors and a novel policy optimization algorithm, Interaction-Perceptive Agentic Policy Optimization (IPA), which assigns credit over semantic interaction chunks rather than individual tokens to improve long-horizon training stability. Empirically, we evaluate ROME within a structured setting and introduce Terminal Bench Pro, a benchmark with improved scale and contamination control. ROME demonstrates strong performance across benchmarks like SWE-bench Verified and Terminal Bench, proving the effectiveness of ALE.

cs.AI↗