arXiv subjects

Jiayi Liu

Publications and source records attributed to Jiayi Liu.

At least 37 records · Page 2Linked to original sources

arXiv2026

Where's Waldo Library? Using Reverse IP Geolocation to Identify Library IPs

Community anchor institutions (CAIs), such as libraries, schools, and community centers, are critical for providing Internet access to un- or under-served individuals and communities. Because many of these institutions are themselves under-provisioned, analyzing the reliability and quality of their Internet service is important. Doing so at scale requires knowing the IP addresses of these institutions so that broadband measurement and policy evaluation can occur. Unfortunately, these IPs are not systematically documented. As a first step towards widespread, scalable evaluation of CAI Internet connectivity, this paper presents Reverse IP Geolocation (RG), a new framework to infer IP addresses from physical address data. A key insight is that CAI street addresses are publicly known, which allows us to identify a candidate set of IPs from commercial geolocation that are likely serving the location associated with a CAI. In this paper, \textbf{we focus on US public libraries}, which offer both geographic diversity across thousands of locations, and some publicly available institutional records (\eg{}WHOIS registrations) that enable systematic validation of our approach. Our approach offers a novel integration of IP geolocation databases, DNS PTR records, WHOIS registrations, broadband provider data, and active measurements to identify IPs likely assigned to libraries and validate them. Based on evaluations, our approach can map a library to its IP prefix approx. half of the time, with coverage across all US states, as well as urban and rural areas. Our results highlight the feasibility of mapping CAI presence in IP space and offer a foundation for large-scale, remote broadband infrastructure evaluation.

cs.NI↗

arXiv2026

Toward User Preference Alignment in LLM Recommendation via Explicit Context Feedback

Traditional recommender systems (RecSys) primarily infer user preferences from implicit signals (such as clicks, watches, and purchases), often neglecting the rich explicit contextual feedback users provide through verbal text, like comments and reviews. This explicit context feedback captures the nuanced reasons behind user decisions regarding their preferences. In addition, it offers critical heterogeneous information for user preference alignment and more explainable recommendations. Overlooking such signals can lead to misaligned user preferences and further reinforce filter bubbles, as algorithms fail to understand the "semantic context" behind user choices. Recent advances in Large Language Models (LLMs) present new opportunities to harness user-generated content for more accurate and diverse recommendations, yet current LLM-based recommendations still focus on using item meta-data and underutilize this resource. In this paper, we advocate for prioritizing explicit context feedback in the next generation of LLM-based RecSys. We review the evolution of recommendation paradigms, highlight the value of context-rich feedback, call for new benchmarks and metrics, and introduce frameworks for integrating explicit user signals into scalable LLM-driven RecSys. Centering on user-preference modeling, we aim to foster more personalized, transparent, and explainable RecSys online platforms.

cs.IR↗

arXiv2026

Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects

We present Artiverse, a diverse and physically grounded dataset of high-quality articulated 3D objects designed for realistic functional modeling and simulation. Artiverse contains 5.4K human-authored objects across a broad range of 88 categories, aggregated from multiple 3D static repositories. Objects are annotated with functional parts, interior structures, realistic kinematic relationships and articulated joints including multi-DoF joints, and physical attributes such as metric scale, material, and mass. We develop a semi-automated annotation pipeline that combines few-shot segmentation, geometric reasoning, and multi-stage human verification to achieve high-quality and efficient annotation, reducing manual annotation time by over 30%. We demonstrate the value of Artiverse on tasks of part mobility analysis, articulated object generation, and physics-based interaction. Artiverse provides a data resource to advance functional understanding for articulated objects.

cs.CV↗

arXiv2026

Learning-Based Adaptive Control for Surgical Robotic Exposure Task on Deformable Tissues

In various surgical procedures, regions of interest (ROIs) such as organs or lesions are often occluded by overlying tissues, requiring surgeons to achieve adequate exposure for precise intervention. However, the irregular geometry, nonlinear biomechanical properties of overlying tissues, and limited intraoperative visibility of the ROI pose significant challenges to the autonomous execution of tissue retraction. To address this, we formulate a realistic model of the tissue retraction task and propose a learning-based adaptive control framework for achieving ROI exposure. The method optimizes control inputs online by monitoring changes in the visual boundary of the tissue, while leveraging a deep deformation estimation model trained on simulation data to identify the optimal grasping point and ensure the convergence and safety of the adaptive controller. Through simulations and real-world experiments on different deformable materials, it has been demonstrated that this framework exhibits zero-shot adaptation to similar tasks and can complete the autonomous retraction process, from initial grasp selection to full ROI exposure. Therefore, it has the potential to be applied in actual surgical assistance scenarios.

cs.RO↗

arXiv2026

Network-Adaptive Cloud Processing for Visual Neuroprostheses

Cloud-based machine learning is increasingly explored as a preprocessing strategy for next-generation visual neuroprostheses, where advanced scene understanding may exceed the computational and energy constraints of battery-powered visual processing units. Offloading computation to remote servers enables the use of state-of-the-art vision models, but also introduces sensitivity to network latency, jitter, and packet loss, which can disrupt the temporal consistency of the delivered neural stimulus. In this work, we examine the feasibility of cloud-assisted visual preprocessing for artificial vision by framing remote inference as a perceptually constrained systems problem. We present a network-adaptive cloud-assisted pipeline in which real-time round-trip-time feedback is used to dynamically modulate image resolution, compression, and transmission rate, explicitly prioritizing temporal continuity under adverse network conditions. PIDNet is used as a fixed real-time semantic segmentation backbone, allowing us to isolate how network-adaptive input encoding affects communication delay, inference time, and perceptual fidelity. Results show that adaptive visual encoding substantially reduces end-to-end latency during network congestion, with only modest degradation of global scene structure, while boundary precision degrades more sharply. Together, these findings delineate operating regimes in which cloud-assisted preprocessing may remain viable for future visual neuroprostheses and underscore the importance of network-aware adaptation for maintaining perceptual stability.

cs.NI↗

arXiv2026

Generating Leakage-Free Benchmarks for Robust RAG Evaluation

Retrieval-augmented generation (RAG) is widely used to augment large language models (LLMs) with external knowledge. However, many benchmark datasets, designed to test RAG performance, comprise many questions that can already be answered from an LLM's parametric memory. This leads to unreliable evaluation. We refer to this phenomenon as knowledge leakage: cases where RAG tasks are solvable without retrieval. This issue worsens over time due to benchmark aging. As benchmarks are reused for training, their contents are increasingly absorbed into model parameters, making them less effective for evaluating retrieval. We introduce SeedRG, a semi-synthetic benchmark generation pipeline that mitigates knowledge leakage and addresses the issue of benchmark aging. Starting from a seed benchmark dataset, SeedRG extracts a reasoning graph from question-context pairs to capture their underlying reasoning structure, and then generates new examples via type-constrained entity replacement. This process produces structurally similar but novel instances that are unlikely to exist in the model's parametric knowledge, while preserving the original reasoning patterns. To ensure quality, we incorporate two verification steps: (1) a reasoning-graph consistency check to maintain task difficulty, and (2) a knowledge-leakage filter to exclude instances answerable without retrieval.

cs.CL↗

arXiv2026

Decentralized Rank Scheduling for Energy-Constrained Multi-Task Federated Fine-Tuning in Edge-Assisted IoV Networks

Large-scale Internet of Vehicles (IoV) deployments increasingly demand the on-device adaptation of foundation models to support diverse, mission-critical perception tasks. While federated fine-tuning offers a promising solution for efficient model specialization, existing approaches often struggle to reconcile the inherent conflict between stringent global energy budgets, heterogeneous task demands, and the high volatility of vehicular network connectivity. In this work, we introduce a hierarchical, adaptive framework that decouples multi-task fine-tuning into two interdependent optimization phases. First, we implement a feedback-loop mechanism at the infrastructure level that dynamically redistributes global energy budgets across concurrent tasks based on real-time convergence dynamics and resource utilization. Second, at the vehicle level, we formulate intra-task rank selection as an energy-constrained online learning problem, solved via a novel primal-dual bandit algorithm, UCB-DUAL, which provides theoretical guarantees on sublinear regret. Our approach effectively internalizes global energy constraints into local decision-making, allowing vehicles to autonomously navigate the complex trade-off between model accuracy, latency, and power consumption. Empirical evaluations using a large-scale IoV simulator, driven by real-world trajectory data, confirm that our proposed method significantly outperforms current federated fine-tuning baselines, offering a robust and scalable solution for resource-constrained vehicular intelligence.

cs.LG↗

arXiv2026

Towards a Robust Estimate of the Solar Photospheric Poynting Flux and Helicity Flux

The observed solar photospheric magnetic fields and Doppler velocities are frequently used to quantify the Poynting flux and helicity flux. Multiple methods have been developed for this purpose, but their estimates of the Poynting flux and helicity flux often differ from one another. Here we study the performance of three widely used methods on NOAA active region 12673: "PTD-Doppler-FLCT Ideal" (PDFI), "Differential Affine Velocity Estimator for Vector Magnetograms" (DAVE4VM), and an extension of the latter with Doppler velocity constraint (DAVE4VMwDV). We find that the values of the accumulated energy and helicity differ significantly between the three methods, even in signs. Using the Helmholtz-Hodge decomposition, we show that Doppler velocity can contribute significantly to the Poynting flux and helicity flux through the non-inductive (curl-free) electric field. The different, ad hoc treatments of the Doppler and transverse velocities in three methods are directly responsible for the discrepancies. We discuss the desired future observations that can better constrain these methods.

astro-ph.SR↗

arXiv2026

Synthetic Sandbox for Training Machine Learning Engineering Agents

As large language model agents advance beyond software engineering (SWE) tasks toward machine learning engineering (MLE), verifying agent behavior becomes orders of magnitude more expensive: while SWE tasks can be verified via fast-executing unit tests, MLE verification requires running full ML pipelines -- data preprocessing, model training, and metric evaluation -- on large datasets at each rollout step, rendering trajectory-wise on-policy reinforcement learning (RL) prohibitively slow. Existing approaches retreat to supervised fine-tuning (SFT) or offline proxy rewards, sacrificing the exploration and generalization benefits of on-policy RL. We observe that sandbox data size is the primary source of this bottleneck. Based on this insight, we introduce SandMLE, a multi-agent framework that generates diverse, verifiable synthetic MLE environments from a small number of seed tasks, preserving the structural and technical complexity of real-world problems while constraining datasets to micro-scale (each task is paired with only 50-200 training samples). Through extensive experiments, we show that SandMLE reduces execution time by over 13 times, enabling large-scale, on-policy trajectory-wise RL for the first time in the MLE domain. On MLE-bench-lite, SandMLE yields significant gains over SFT baselines across Qwen3-8B, 14B, and 30B-A3B, with relative medal rate improvements ranging from 20.3% to 66.9%. Furthermore, the trained policy generalizes across unseen agentic scaffolds, achieving up to 32.4% better HumanRank score on MLE-Dojo.

cs.CL↗

arXiv2026

LLM-Driven Reasoning for Constraint-Aware Feature Selection in Industrial Systems

Feature selection is a crucial step in large-scale industrial machine learning systems, directly affecting model accuracy, efficiency, and maintainability. Traditional feature selection methods rely on labeled data and statistical heuristics, making them difficult to apply in production environments where labeled data are limited and multiple operational constraints must be satisfied. To address this, we propose Model Feature Agent (MoFA), a model-driven framework that performs sequential, reasoning-based feature selection using both semantic and quantitative feature information. MoFA incorporates feature definitions, importance scores, correlations, and metadata (e.g., feature groups or types) into structured prompts and selects features through interpretable, constraint-aware reasoning. We evaluate MoFA in three real-world industrial applications: (1) True Interest and Time-Worthiness Prediction, where it improves accuracy while reducing feature group complexity, (2) Value Model Enhancement, where it discovers high-order interaction terms that yield substantial engagement gains in online experiments, and (3) Notification Behavior Prediction, where it selects compact, high-value feature subsets that improve both model accuracy and inference efficiency. Together, these results demonstrate the practicality and effectiveness of LLM-based reasoning for feature selection in real production systems.

cs.CL↗

arXiv2026

QuarkMedBench: A Real-World Scenario Driven Benchmark for Evaluating Large Language Models

While Large Language Models (LLMs) excel on standardized medical exams, high scores often fail to translate to high-quality responses for real-world medical queries. Current evaluations rely heavily on multiple-choice questions, failing to capture the unstructured, ambiguous, and long-tail complexities inherent in genuine user inquiries. To bridge this gap, we introduce QuarkMedBench, an ecologically valid benchmark tailored for real-world medical LLM assessment. We compiled a massive dataset spanning Clinical Care, Wellness Health, and Professional Inquiry, comprising 20,821 single-turn queries and 3,853 multi-turn sessions. To objectively evaluate open-ended answers, we propose an automated scoring framework that integrates multi-model consensus with evidence-based retrieval to dynamically generate 220,617 fine-grained scoring rubrics (~9.8 per query). During evaluation, hierarchical weighting and safety constraints structurally quantify medical accuracy, key-point coverage, and risk interception, effectively mitigating the high costs and subjectivity of human grading. Experimental results demonstrate that the generated rubrics achieve a 91.8% concordance rate with clinical expert blind audits, establishing highly dependable medical reliability. Crucially, baseline evaluations on this benchmark reveal significant performance disparities among state-of-the-art models when navigating real-world clinical nuances, highlighting the limitations of conventional exam-based metrics. Ultimately, QuarkMedBench establishes a rigorous, reproducible yardstick for measuring LLM performance on complex health issues, while its framework inherently supports dynamic knowledge updates to prevent benchmark obsolescence.

cs.CL↗

arXiv2026

Refinements to the Solar Polar Magnetic Flux: Implications from Inversion Methodologies

The magnetic fields in the solar polar region are important to our understanding of the internal dynamo process, the global coronal structure, and the origin of the solar wind. The inference of polar fields based on spectropolarimetric observation is highly model-dependent and can suffer from various systematic effects. Here we analyze a raster map of the southern polar region taken by the Hinode Spectro-Polarimeter, utilizing the Stokes Inversion based on Response functions code. The inversions provide height-dependent vector magnetic field maps between optical depths $\log_{10}τ= -2$ and $0$. We examine the impact on the total magnetic flux estimate from adopting (1) 1- vs 2-component atmospheric models via a "filling factor" parameter and (2) different analysis schemes. At $\log_{10}τ= -1.5$, the polar magnetic flux is estimated to be $(1.84 \pm 0.03) \times 10^{21}$ Mx and $(1.38 \pm 0.02) \times 10^{21}$ Mx under the 1- and 2-component atmosphere assumption, respectively. The magnetic flux is approximately constant or increases slightly with height, respectively. We find that the 2-component (1-component) configuration is preferred for 58.3% (32.3%) of the pixels. Different initial guesses, including the input atmosphere model and the filling factor, as well as different inversion settings, can significantly affect the results, especially for locations with weaker polarization signals. Our work highlights the importance of including unresolved magnetic structures or stray light into consideration. Model degeneracy and the convergence to local minima limit the precision of the polar magnetic flux inference (no better than several tens of percent in this case). Higher-resolution observations and advanced inversion and disambiguation algorithms may alleviate these limitations.

astro-ph.SR↗

arXiv2026

ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning

Low-rank adapters (LoRAs) are a parameter-efficient finetuning technique that injects trainable low-rank matrices into pretrained models to adapt them to new tasks. Mixture-of-LoRAs models expand neural networks efficiently by routing each layer input to a small subset of specialized LoRAs of the layer. Existing Mixture-of-LoRAs routers assign a learned routing weight to each LoRA to enable end-to-end training of the router. Despite their empirical promise, we observe that the routing weights are typically extremely imbalanced across LoRAs in practice, where only one or two LoRAs often dominate the routing weights. This essentially limits the number of effective LoRAs and thus severely hinders the expressive power of existing Mixture-of-LoRAs models. In this work, we attribute this weakness to the nature of learnable routing weights and rethink the fundamental design of the router. To address this critical issue, we propose a new router designed that we call Reinforcement Routing for Mixture-of-LoRAs (ReMix). Our key idea is using non-learnable routing weights to ensure all active LoRAs to be equally effective, with no LoRA dominating the routing weights. However, our routers cannot be trained directly via gradient descent due to our non-learnable routing weights. Hence, we further propose an unbiased gradient estimator for the router by employing the reinforce leave-one-out (RLOO) technique, where we regard the supervision loss as the reward and the router as the policy in reinforcement learning. Our gradient estimator also enables to scale up training compute to boost the predictive performance of our ReMix. Extensive experiments demonstrate that our proposed ReMix significantly outperform state-of-the-art parameter-efficient finetuning methods under a comparable number of activated parameters.

cs.LG↗

arXiv2026

EgoTraj-Bench: Towards Robust Trajectory Prediction Under Ego-view Noisy Observations

Reliable trajectory prediction from an ego-centric perspective is crucial for robotic navigation in human-centric environments. However, existing methods typically assume noiseless observation histories, failing to account for the perceptual artifacts inherent in first-person vision, such as occlusions, ID switches, and tracking drift. This discrepancy between training assumptions and deployment reality severely limits model robustness. To bridge this gap, we introduce EgoTraj-Bench, built upon TBD dataset, which is the first real-world benchmark that aligns noisy, first-person visual histories with clean, bird's-eye-view future trajectories, enabling robust learning under realistic perceptual constraints. Building on this benchmark, we propose BiFlow, a dual-stream flow matching model that concurrently denoises historical observations and forecasts future motion. To better model agent intent, BiFlow incorporates our EgoAnchor mechanism, which conditions the prediction decoder on distilled historical features via feature modulation. Extensive experiments show that BiFlow achieves state-of-the-art performance, reducing minADE and minFDE by 10-15% on average and demonstrating superior robustness. We anticipate that our benchmark and model will provide a critical foundation for robust real-world ego-centric trajectory prediction. The benchmark library is available at: https://github.com/zoeyliu1999/EgoTraj-Bench.

cs.CV↗

arXiv2026

Quark Medical Alignment: A Holistic Multi-Dimensional Alignment and Collaborative Optimization Paradigm

While reinforcement learning for large language model alignment has progressed rapidly in recent years, transferring these paradigms to high-stakes medical question answering reveals a fundamental paradigm mismatch. Reinforcement Learning from Human Feedback relies on preference annotations that are prohibitively expensive and often fail to reflect the absolute correctness of medical facts. Reinforcement Learning from Verifiable Rewards lacks effective automatic verifiers and struggles to handle complex clinical contexts. Meanwhile, medical alignment requires the simultaneous optimization of correctness, safety, and compliance, yet multi-objective heterogeneous reward signals are prone to scale mismatch and optimization conflicts. To address these challenges, we propose a robust medical alignment paradigm. We first construct a holistic multi-dimensional medical alignment matrix that decomposes alignment objectives into four categories: fundamental capabilities, expert knowledge, online feedback, and format specifications. Within each category, we establish a closed loop of where observable metrics inform attributable diagnosis, which in turn drives optimizable rewards, thereby providing fine-grained, high-resolution supervision signals for subsequent iterative optimization. To resolve gradient domination and optimization instability problem caused by heterogeneous signals, we further propose a unified optimization mechanism. This mechanism employs Reference-Frozen Normalization to align reward scales and implements a Tri-Factor Adaptive Dynamic Weighting strategy to achieve collaborative optimization that is weakness-oriented, risk-prioritized, and redundancy-reducing. Experimental results demonstrate the effectiveness of our proposed paradigm in real-world medical scenario evaluations, establishing a new paradigm for complex alignment in vertical domains.

cs.AI↗

arXiv2026

Leveraging Computerized Adaptive Testing for Cost-effective Evaluation of Large Language Models in Medical Benchmarking

The rapid proliferation of large language models (LLMs) in healthcare creates an urgent need for scalable and psychometrically sound evaluation methods. Conventional static benchmarks are costly to administer repeatedly, vulnerable to data contamination, and lack calibrated measurement properties for fine-grained performance tracking. We propose and validate a computerized adaptive testing (CAT) framework grounded in item response theory (IRT) for efficient assessment of standardized medical knowledge in LLMs. The study comprises a two-phase design: a Monte Carlo simulation to identify optimal CAT configurations and an empirical evaluation of 38 LLMs using a human-calibrated medical item bank. Each model completed both the full item bank and an adaptive test that dynamically selected items based on real-time ability estimates and terminated upon reaching a predefined reliability threshold (standard error <= 0.3). Results show that CAT-derived proficiency estimates achieved a near-perfect correlation with full-bank estimates (r = 0.988) while using only 1.3 percent of the items. Evaluation time was reduced from several hours to minutes per model, with substantial reductions in token usage and computational cost, while preserving inter-model performance rankings. This work establishes a psychometric framework for rapid, low-cost benchmarking of foundational medical knowledge in LLMs. The proposed adaptive methodology is intended as a standardized pre-screening and continuous monitoring tool and is not a substitute for real-world clinical validation or safety-oriented prospective studies.

cs.CL↗

arXiv2026

Don't Waste It: Guiding Generative Recommenders with Structured Human Priors via Multi-Head Decoding

Optimizing recommender systems for objectives beyond accuracy, such as diversity, novelty, and personalization, is crucial for long-term user satisfaction. To this end, industrial practitioners have accumulated vast amounts of structured domain knowledge, which we term human priors (e.g., item taxonomies, temporal patterns). This knowledge is typically applied through post-hoc adjustments during ranking or post-ranking. However, this approach remains decoupled from the core model learning, which is particularly undesirable as the industry shifts to end-to-end generative recommendation foundation models. On the other hand, many methods targeting these beyond-accuracy objectives often require architecture-specific modifications and discard these valuable human priors by learning user intent in a fully unsupervised manner. Instead of discarding the human priors accumulated over years of practice, we introduce a backbone-agnostic framework that seamlessly integrates these human priors directly into the end-to-end training of generative recommenders. With lightweight, prior-conditioned adapter heads inspired by efficient LLM decoding strategies, our approach guides the model to disentangle user intent along human-understandable axes (e.g., interaction types, long- vs. short-term interests). We also introduce a hierarchical composition strategy for modeling complex interactions across different prior types. Extensive experiments on three large-scale datasets demonstrate that our method significantly enhances both accuracy and beyond-accuracy objectives. We also show that human priors allow the backbone model to more effectively leverage longer context lengths and larger model sizes.

cs.IR↗

arXiv2025

Dynamic Imaging of Periodic Structures using Extreme Ultraviolet Scatterometry

Dynamic scattering and imaging with coherent, ultrafast, extreme ultraviolet (EUV) light sources can resolve charge, phonon and spin processes on their intrinsic length and time scales. However, full field coherent diffraction imaging requires scanning of the sample combined with computational phase retrieval, making it challenging to quickly acquire a large series of dynamic frames. In this work, we demonstrate a technique for extracting dynamic 1D images of the average unit cell in a periodic sample from traditional EUV scatterometry data by analyzing the changing intensities of the far field diffracted orders. Starting from a system of equations relating small changes in far field diffraction to phase and amplitude perturbations at the sample plane, it is shown that under certain conditions, changes to the $n$th diffracted order map exclusively onto the $n$th Fourier component of the perturbation via a closed-form relation. We show through rigorous coupled-wave analysis simulations that our method can provide a good approximation even outside the scalar diffraction theory framework in which it is derived. Finally, we experimentally demonstrate this reconstruction method by exiting 1D nickel nanowires on a diamond substrate using an infrared laser pump pulse, and measuring their relaxation using a time-delayed EUV probe pulse, to visualize nanoscale phonon dynamics.

physics.optics↗