arXiv subjects

Fei Jiang

Publications and source records attributed to Fei Jiang.

At least 19 recordsLinked to original sources

arXiv2026

Testing Processor Contracts in Speculative Decoding Engines

Speculative sampling can accelerate decoding without changing the target distribution. Its standard guarantee assumes that logits processors, which enforce constraints or modify token scores, receive the appropriate token prefix and state at each verification position. We formalize this processor-prefix contract and present BADC (branch-aware differential conformance testing). BADC combines enumerated references on tiny random models, checks of processor inputs and state, and simultaneous confidence bounds on output-event probabilities. Preregistered, source-informed experiments on selected Transformers and llama-cpp-python releases confirm two causes: processors read unverified drafts or advance state without rollback. For one pilot-selected prompt on a trained checkpoint, fresh samples give a 60.26-percentage-point lower bound on the difference in the probability of a predefined first-token event between ordinary and prompt-lookup decoding, with nominal simultaneous 95% coverage under within-arm i.i.d. sampling. Controlled comparisons establish no cause-recovery advantage of directed selection over random selection, while permutation testing detects each tested family at least as often as BADC. These findings connect processor-interface failures to observable decoding differences without establishing diagnostic superiority or workload prevalence.

cs.SE↗

arXiv2026

Latent Residual Reasoning for Ranking in Generative Recommendation

Generative recommendation (GR) models for ranking typically adopt a fast-thinking direct prediction paradigm with strong practical efficiency. However, ranking requires fine-grained scoring across multiple candidate items, while existing GR models still mainly rely on one-shot prediction. This raises the question whether additional inference-time computation can further improve ranking quality. Recently, inspired by Chain-of-Thought (CoT) reasoning in large language models (LLMs), some work has begun to introduce reasoning into recommendation systems. Some of these methods rely on LLM reasoning frameworks to perform explicit reasoning in textual space, but such designs are not suitable for more widely deployed non-textual recommendation models. A more relevant direction is to introduce latent reasoning into ID-based recommendation models. Although recent work has extended latent reasoning to industrial ranking, how successive reasoning steps should improve fine-grained candidate scores remains less explored. To address this problem, we propose Refiner, a latent residual reasoning framework with parameter-efficient fine-tuning for generative ranking. Our approach introduces three key components: (1) a residual reasoning mechanism that progressively refines ranking scores through cumulative additive corrections, (2) history queries that provide condensed user behavior representations to enhance candidate-specific reasoning, and (3) a parameter-efficient fine-tuning strategy that leverages LoRA modules to adapt pre-trained models for latent reasoning. Extensive experiments on two public benchmarks, an offline industrial dataset, and an online A/B test demonstrate that Refiner consistently improves over direct prediction, validating its effectiveness and practical utility.

cs.IR↗

arXiv2026

Re-executing Coding-Agent Evaluations: Unchanged Decisions and Unresolved Policy Risk

Executable tests grade large language model (LLM) coding-agent patches for leaderboards, rewards and self-improvement. Two preregistered re-execution studies returned negative results. SWE-bench Pro v1's offline option rejected none of 59 accepted Go patches whose grading configuration changed. Their exploratory, unweighted upper confidence limit is 4.95% under candidate independence, leaving a 3% exposed-patch risk unresolved; the preregistered estimator uses inverse sampling-probability weights. An extension was inconclusive. In a selected stratum, a reconstructed module cache built from the reference solution's dependencies rejected accepted alternatives from four models that passed with their own dependencies. Re-executing 1,929 selected agent-version/task evaluations from the Darwin Gödel Machine's archive preserved best-agent selection and system-variant ranking, with search history and scores of evaluations not rerun fixed. Exploratory host, image and adapted-grader comparisons also preserved them. Seven of 23 disagreements with archived verdicts did not recur on a second host; rebuilt images changed 16 three-run majority verdicts (0.83%) under four-CPU execution. We provide an evidence-to-claim summary, lessons for grader audits and an anonymous replication package. These results concern accepted patches and fixed-history decisions; general policy safety and adaptive-learning robustness require broader evaluations.

cs.SE↗

arXiv2026

Towards Strategy-Level RSI for Skill-Augmented Agents: Learning When to Reuse Skills from Execution Feedback

Long-running agents accumulate reusable Skills, but a Skill that is semantically relevant to a task is not necessarily worth loading in the current state. We study the applicability question that arises once a candidate Skill is known: should it be loaded in the current state? We propose SkillApt, which uses matched WITH/WITHOUT Skill executions on the same task state as persistent evidence, estimates the conditional marginal utility of the Skill, and chooses LOAD or ABSTAIN accordingly. The base model, agent architecture, and Skill contents stay fixed; only the external deployment policy changes. We call this constrained setting strategy-level recursive self-improvement (Strategy-Level RSI). On 20 Skills and 160 held-out states, as paired evidence accumulates, SkillApt's task success rises from 81.9% under a cold start to 91.3%, matching a strong zero-shot LLM controller; yet SkillApt activates Skills on only 26.3% of states, versus 98.8% for the zero-shot controller. A hard-candidate study shows that non-optimal Skills mostly leave correctness unchanged while raising execution cost, and occasionally cause correctness harm. An ablation shows that a history recording only WITH success makes the policy load almost everywhere, whereas paired evidence substantially improves selectivity. These results indicate that relevance is not applicability: the main effect of execution evidence is not to make the model stronger but to change how existing Skills are deployed, moving the system from near-always loading to selective reuse.

cs.MA↗

arXiv2026

TagPR: Tag-Guided Process Supervision for Personalization Reasoning in Large Language Models

Recent advancements have endowed Large Language Models with impressive general reasoning capabilities. However, these reasoning models often perform worse than non-reasoning models on personalization tasks. While some methods use outcome-based RL to improve personalization reasoning, they fail to supervise the reasoning process. As a result, models may reach correct answers through flawed reasoning chains, limiting further improvement. To address this, we propose TagPR, a novel framework that adds semantic tags to the reasoning process for step-by-step guidance. TagPR first automatically generates a structured, tagged dataset for Supervised Fine-Tuning. It then employs a multi-stage RL process guided by a composite reward signal, which integrates tag-based process supervision with a novel Personalization Reward Model with User Embeddings to achieve fine-grained alignment with user-specific logic. Extensive experiments on public LaMP, LongLaMP, PGraphRAG, and a self-constructed dataset demonstrate that our approach achieves state-of-the-art results, delivering an average improvement of 32.65% over the base model across all LaMP benchmark tasks. Our work demonstrates that tag-guided process supervision is an effective approach for personalization reasoning.

cs.CL↗

arXiv2026

Photorealistic Novel View Synthesis of Human Faces using Next-Scale Transformers

Photorealistic novel view synthesis of people remains challenging at high spatial resolutions and across multiple target cameras, where preserving identity, fine appearance details, and geometric coherence is critical. We build on the next-scale autoregressive paradigm and adapt it for human-centric view synthesis by enabling higher image resolutions, multi-view outputs and stronger cross-view consistency in a single forward pass. We train on a synthetic dataset of human faces spanning diverse identities and apparel. Contrary to diffusion models, this paradigm does not need 2D pre-training and, thanks to its next-scale architecture, it benefits from lower-resolution, general-purpose pre-trainings, with the full-sized purpose-specific images being used only in the last training stages. This enables our architecture to converge with a smaller amount of purpose-specific training data, allowing us to use a smaller but more realistic training dataset. The resulting model produces sharp and realistic views, with the option to synthesize multiple novel viewpoints simultaneously for improved agreement across views. Empirically, we observe gains in perceptual fidelity and cross-view coherence on human subjects, demonstrating that next-scale autoregression is an effective backbone for scalable, multi-output human view synthesis. We also couple our pipeline with an existing transformer-based model for pixel-aligned 3D gaussian lifting from multi-view facial inputs, resulting in accurate and photorealistic 3D models of human faces.

cs.CV↗

arXiv2026

A Hybrid Statistical Learning Framework for Capability-Based Decision Support in Manufacturing

Process capability indices are widely used in manufacturing quality control, but capability approval is often implemented by directly thresholding finite-sample estimates, which can produce unstable and poorly calibrated decisions near the approval boundary. This paper develops a hybrid statistical--learning framework for capability-based decision support in manufacturing. The proposed UC-Cap approach combines a statistically grounded capability baseline with a residual learning component that uses process, distributional, specification-related, and measurement-related features to refine capability-decision risk estimates under non-ideal manufacturing conditions. The statistical baseline preserves the interpretability of classical capability analysis, while the learning component provides data-driven correction for systematic deviations arising from non-normality, measurement effects, and finite-sample variability. A nested Monte Carlo evaluation is introduced to assess probabilistic calibration under controlled synthetic settings, and an empirical manufacturing study is used to examine decision behavior under realistic capability data. Results show that deterministic thresholding can lead to substantial instability and miscalibration in near-boundary regimes, whereas the proposed framework provides calibrated risk estimates, interpretable decision outputs, and improved support for capability approval decisions. The framework is compatible with existing capability-analysis workflows and can be integrated into manufacturing quality decision-support systems.

stat.AP↗

arXiv2026

MTGenRec: An Efficient Distributed Training System for Generative Recommendation Models in Meituan

Recommendation is crucial for both user experience and company revenue in Meituan as a leading lifestyle company, and generative recommendation models (GRMs) are shown to produce quality recommendations recently. However, existing systems are limited by insufficient functionality support and inefficient implementations for training GRMs in industrial scenarios. As such, we introduce MTGenRec as an efficient and scalable system for GRM training. Specifically, to handle real-time insertions/deletions of sparse embeddings, MTGenRec employs dynamic hash tables to replace static ones. To improve training efficiency, MTGenRec conducts dynamic sequence balancing to address the computation load imbalances among GPUs and adopts feature ID deduplication alongside automatic table merging to accelerate embedding lookup. Extensive experiments show that MTGenRec improves training throughput by $1.6\times -- 2.4\times$ while achieving good scalability when running over 100 GPUs. MTGenRec has been deployed for many applications in Meituan and is now handling hundreds of millions of requests on a daily basis. On the delivery platform, we observe a 1.22% growth in user order volume and a 1.31% enhancement in online PV_CTR.

cs.DC↗

arXiv2026

Bayesian Deployment Approval for Learned Landing Controllers under Finite Rollout Validation

Reinforcement learning and data-driven autonomous controllers are commonly evaluated using cumulative reward and empirical success frequency under finite simulation trajectories. However, such empirical metrics do not necessarily provide sufficient statistical evidence regarding deployment readiness under uncertainty. This work develops a Bayesian approval framework for learned autonomous landing controllers under finite rollout evidence. A probabilistic landing capability formulation is introduced based on touchdown safety satisfaction under uncertain operating conditions, while Bayesian posterior inference is used to quantify uncertainty regarding the true deployment capability of learned policies. Posterior approval probability and posterior deployment risk are further introduced for deployment-oriented evaluation, together with a sequential validation framework supporting approve/reject/continue decisions during progressive rollout testing. Simulation experiments using PPO and SAC controllers demonstrate that empirical success and reward optimization may produce overconfident deployment interpretation under limited validation evidence, whereas posterior approval inference provides a more uncertainty-calibrated assessment of deployment readiness. The proposed framework provides a practical statistical connection between conventional reinforcement-learning evaluation and deployment-oriented validation under uncertainty and may be generalized to broader classes of learned autonomous systems.

cs.LG↗

arXiv2026

Latent Dynamics for Full Body Avatar Animation

Pose-driven full-body avatars built on neural rendering produce high-quality novel views of a captured subject. Yet loose clothing and other dynamic elements deform in ways pose alone cannot explain: the same pose can correspond to many different states, because their motion depends on history, inertia, and contact. Explicit simulation and layered-garment methods can model such dynamics, but they require either a dedicated garment template, which raw multi-view capture does not naturally provide, or a test-time physics simulator with non-trivial runtime cost. A parallel line of work learns data-driven clothing avatars that avoid explicit garment layers. These methods add an auxiliary latent for variation beyond pose; at inference, they fix it, regress it from pose, or retrieve it from training data, without explicitly modeling how the latent evolves with its own dynamics. Additionally, even in everyday motion with loose clothing, existing architectures often struggle to capture fine-grained detail, producing blurry renderings and temporal artifacts. We augment a pose-conditioned 3D Gaussian avatar with a transformer-based decoder and a dynamics residual latent that captures temporal appearance and geometry variation beyond the driving signals. At inference, a learned latent dynamics model evolves the residual latent from a short pose history and the previous latent state. The model decomposes each update into driving, restoring, and dissipative forces, producing temporally coherent, history-dependent rollouts with negligible added cost. Different initial conditions yield diverse yet plausible motion trajectories, and the force decomposition exposes controls such as stiffness. Across nine captured sequences of everyday motion with diverse loose garments, quantitative metrics and a perceptual user study show improved animation quality over recent data-driven baselines.

cs.CV↗

arXiv2026

Risk-Calibrated Process Capability Approval with Finite Samples

Process capability indices such as $C_{pk}$ are widely used in manufacturing to support supplier qualification, pilot-build release, and production approval. In practice, approval decisions are often based on deterministic threshold rules of the form $\widehat{C}_{pk} \ge C_0$. Because $\widehat{C}_{pk}$ is estimated from finite samples, however, such decisions are inherently stochastic, especially when the true capability lies near the approval threshold. This paper develops a risk-calibrated decision framework for process capability approval that explicitly accounts for estimation uncertainty and asymmetric operational loss. Capability approval is formulated as a binary statistical decision problem, leading to a rule of the form $\widehat{C}_{pk} \ge C_0 + k\,SE(\widehat{C}_{pk})$, where the calibration constant $k$ is determined either by a tolerable failure probability or by a false-accept/false-reject cost ratio. The resulting formulation unifies several commonly used procedures, including deterministic thresholding, lower confidence bound rules, and probability-based approval rules, and naturally extends them to cost-sensitive decision rules derived from asymmetric operational loss. Simulation experiments and an industrial case study show that risk calibration primarily affects near-threshold decisions, improves approval stability, and can substantially reduce expected operational loss when false acceptance is more costly than false rejection.

stat.AP↗

arXiv2026

Nonlinear Amplification of Finite-Sample Uncertainty in Capability-Based Decisions

This paper studies the propagation of finite-sample uncertainty under nonlinear transformations commonly used in statistical decision systems. In particular, we consider process capability indices, which are widely used in manufacturing practice but are estimated from finite samples, rendering the resulting approval decisions inherently uncertain. We show that such uncertainty cannot be fully explained by estimator variability alone, but is substantially influenced by a nonlinear amplification mechanism through which capability uncertainty is transformed into defect-risk metrics. While capability estimators vary approximately linearly with process dispersion, defect probabilities depend on tail curvature, causing small estimation errors to be disproportionately amplified in measures such as defect probability and parts-per-million (PPM) rates. Consequently, capability assessments that appear stable in index space may exhibit substantial variability in defect-risk space, particularly near decision thresholds. This insight provides a unified explanation of finite-sample decision instability, motivates reliability-aware decision formulations, and links sample-size requirements directly to decision reliability. Monte Carlo simulations and industrial data analyses validate the proposed mechanism and demonstrate its practical implications, including the impact of distributional assumptions on defect-risk estimation.

stat.AP↗

arXiv2026

On Global-in-time Solutions of Incompressible MHD Equations with Small Alfvén Numbers

In 1965 Kraichnan pointed out that a sufficiently strong background magnetic field, i.e. the case of small Alfvén number, will reduce the nonlinear interaction and inhibit the formation of strong gradients in the magnetohydrodynamic (abbr. MHD) system with $μ=ν\geqslant 0$, where $μ$ and $ν$ are the coefficients of kinematic viscosity and resistivity resp.. This means that the MHD system with $μ=ν\geqslant 0$ admits global-in-time large perturbation solutions with small Alfvén numbers. The existence of such large perturbation solutions was first mathematically verified in Hölder spaces by Bardos--Sulem--Sulem for the case $μ=ν= 0$ in 1988, and in Sobolev spaces by Cai--Cui--Jiang--Liu for the case $μ=ν> 0$ recently. In this paper, we further found a similar result for the general case ``$μ>0$ and $ν>0$", and provide a rigorous proof by developing a new approach, which includes a key bilinear estimate for dealing with the nonlinear interaction terms. Moreover both additional results for the vanishing behavior of the nonlinear interaction and the small Alfvén number limit of solutions are also established.

math.AP↗

arXiv2026

MTServe: Efficient Serving for Generative Recommendation Models with Hierarchical Caches

Generative recommendation (GR) offers superior modeling capabilities but suffers from prohibitive inference costs due to the repeated encoding of long user histories. While cross-request Key-Value (KV) cache reuse presents a significant optimization opportunity, the massive scale of individual user states creates a storage explosion that far exceeds physical GPU limits. We propose MTServe, a hierarchical cache management system that virtualizes GPU memory by leveraging host RAM as a scalable backup store. To bridge the I/O gap between tiers, MTServe introduces a suite of system-level optimizations, including a hybrid storage layout, an asynchronous data transfer pipeline, and a locality-driven replacement policy. On both public and production datasets, MTServe delivers up to 3.1* speedup while maintaining near-perfect hit ratios (>98.5%).

cs.LG↗

arXiv2026

Practical Process Capability Indices Workflows

This paper presents a comprehensive review of univariate process capability indices (PCIs), which are critical metrics for assessing how effectively a manufacturing process satisfies customer specifications based on a single quality characteristic. The primary objective of this review is to develop practical procedural workflows for conducting process capability analysis under various preconditions, including those less frequently addressed scenarios in existing literature. Key analytical components, such as outlier detection, normality test, and best distribution fitting, are integrated into the proposed framework to ensure accurate and robust capability assessments. By systematically evaluating a range of methodologies, this study offers guidance for researchers and practitioners in selecting the most appropriate PCIs for specific process conditions. Ultimately, the work aims to simplify the complexity of PCI analysis while enhancing its precision and utility in quality control and process improvement efforts.

stat.AP↗

arXiv2026

DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain

Recent advancements in Vision-Language Models (VLMs) have revolutionized general visual understanding. However, their application in the food domain remains constrained by benchmarks that rely on coarse-grained categories, single-view imagery, and inaccurate metadata. To bridge this gap, we introduce DiningBench, a hierarchical, multi-view benchmark designed to evaluate VLMs across three levels of cognitive complexity: Fine-Grained Classification, Nutrition Estimation, and Visual Question Answering. Unlike previous datasets, DiningBench comprises 3,021 distinct dishes with an average of 5.27 images per entry, incorporating fine-grained "hard" negatives from identical menus and rigorous, verification-based nutritional data. We conduct an extensive evaluation of 29 state-of-the-art open-source and proprietary models. Our experiments reveal that while current VLMs excel at general reasoning, they struggle significantly with fine-grained visual discrimination and precise nutritional reasoning. Furthermore, we systematically investigate the impact of multi-view inputs and Chain-of-Thought reasoning, identifying five primary failure modes. DiningBench serves as a challenging testbed to drive the next generation of food-centric VLM research. All codes are released in https://github.com/meituan/DiningBench.

cs.CV↗

arXiv2026

Nested Deep Learning Model Towards A Foundation Model for Brain Signal Data

Epilepsy affects around 50 million people globally. Electroencephalography (EEG) or Magnetoencephalography (MEG) based spike detection plays a crucial role in diagnosis and treatment. Manual spike identification is time-consuming and requires specialized training that further limits the number of qualified professionals. To ease the difficulty, various algorithmic approaches have been developed. However, the existing methods face challenges in handling varying channel configurations and in identifying the specific channels where the spikes originate. A novel Nested Deep Learning (NDL) framework is proposed to overcome these limitations. NDL applies a weighted combination of signals across all channels, ensuring adaptability to different channel setups, and allows clinicians to identify key channels more accurately. Through theoretical analysis and empirical validation on real EEG/MEG datasets, NDL is shown to improve prediction accuracy, achieve channel localization, support cross-modality data integration, and adapt to various neurophysiological applications.

stat.ML↗

arXiv2026

Finite-Sample Decision Instability in Threshold-Based Process Capability Approval

Process capability indices such as $C_{pk}$ are widely used in manufacturing quality control to support supplier qualification and product release decisions based on fixed acceptance thresholds (e.g., $C_{pk} \geq 1.33$). In practice, these decisions rely on sample-based estimates computed from moderate sample sizes ($n \approx$ 20-50), yet the stochastic nature of the estimator is often overlooked when interpreting threshold compliance. This study establishes a local asymptotic characterization of decision behavior when the true process capability lies near a fixed threshold. Under standard regularity conditions, if the true capability equals the threshold, the acceptance probability converges to 0.5 as sample size increases, implying that a fixed $C_{pk}$ gate embeds an inherent boundary decision risk even under ideal distributional assumptions. When the true capability deviates from the threshold by $O(n^{-1/2})$, the decision probability converges to a non-degenerate limit governed by a scaled signal-to-noise ratio. Monte Carlo simulations and an empirical study on 880 manufacturing dimensions demonstrate substantial resampling-based decision instability near the commonly used 1.33 criterion. These findings provide a probabilistic interpretation of threshold-based capability decisions and quantitative guidance for assessing boundary-induced release risk in engineering practice.

stat.AP↗