Searcharxiv⌕ Search

arXiv subjects

Jun Yang

Publications and source records attributed to Jun Yang.

At least 37 records · Page 2Linked to original sources
arXiv2026

HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses

Harness design plays a critical role in agent performance by shaping how large language models (LLMs) perceive, reason over, and act within executable environments. Recent work has proposed automatic harness evolution, which iteratively improves the harness from agent--environment interactions. However, existing methods often overfit to the evolution tasks, rely exclusively on trajectory-derived signals, and optimize harness components jointly, causing interference across components. We propose HarnessCompass, a novel automatic harness evolution framework built around constrained evolution, proactive feedback, and component-wise optimization. HarnessCompass first enforces global constraints on evolution, restricting modifications to task-agnostic harness changes that generalize beyond the evolution tasks. It then augments trajectory-derived evidence with proactive first-person feedback from the agent about harness usage, yielding richer signals for evolution. Finally, it decouples the optimization of different harness components before consolidating them into a unified harness, reducing cross-component interference while preserving component synergy. On SWE-bench Verified with GPT-5.4, HarnessCompass improves Pass@1 from 54\% to 66\% in only 5 evolution iterations, outperforming AHE in both effectiveness and evolution efficiency. In addition, the evolved harness transfers effectively to held-out tasks and other models, demonstrating substantially stronger generalization than prior automatic harness evolution methods.

cs.LG↗
arXiv2026

MEGRAG: Multi-Granular Evidence Graphs for Answer-Aware Multi-Hop RAG

Multi-hop question answering is a fundamental challenge in retrieval-augmented generation (RAG), because deriving an answer requires integrating dispersed evidence. Iterative RAG (iRAG) is widely used for this challenge, but existing methods have two limitations. First, most methods still support each reasoning step with single-granularity evidence, making it difficult to balance information density and contextual noise. Second, existing methods often answer the original question only after aggregating evidence retrieved across intermediate steps, so redundant evidence and intermediate retrieval errors may accumulate and degrade the final answer. To address these limitations, we propose MEGRAG, an answer-aware framework that represents multi-hop reasoning as a path-structured multi-granular evidence graph. Offline, MEGRAG links passages to their sentences and extracted triples through a cross-granularity index. Online, it retrieves passages for the current query and selects aligned evidence, starting with compact triples and adding sentence or passage context as needed. MEGRAG uses the resulting intermediate answer and prior reasoning to decide whether the Initial Query has been resolved. If not, it identifies the missing information and formulates a focused next query; otherwise, it stops retrieval and returns the answer. Extensive experiments demonstrate consistent gains over a diverse set of RAG baselines.

cs.AI↗
arXiv2026

Model-Agnostic Meta-Learning Initialization for Distributed Multichannel Active Noise Control

Distributed multichannel active noise control (DMCANC) has emerged as a scalable framework for large-area noise reduction, where multiple nodes operate local single-channel ANC controllers and exchange essential information to achieve global control. A key limitation of existing DMCANC implementations lies in their reliance on zero or random initialization, which leads to slow convergence of adaptive filters and restricts the efficiency of internode collaboration. To address this issue, this paper introduces a model-agnostic meta-learning (MAML) based initialization strategy for DMCANC. By aggregating heterogeneous acoustic characteristics across nodes-ncluding primary and secondary paths-a MAML framework is trained to learn an initialization that generalizes effectively across distributed ANC systems. The MAML initialization is then deployed to all nodes to improve convergence speed under both stationary and time-varying noise conditions. Numerical simulations applied on broadband and real-world noise demonstrate that the proposed algorithms achieves substantially faster convergence and improved noise reduction performance compared with conventional DMCANC, highlighting the potential of MAML initialization as an effective method for large-scale ANC.

eess.AS↗
arXiv2026

ParasGB: A Graph Benchmark Suite for Parasitic Estimation on AMS Circuits

As chip manufacturing processes advance to deep submicron nodes, parasitic interconnect effects increasingly dominate the performance of analog and mixed-signal (AMS) circuits and often lead to costly layout iterations. This makes early-stage estimation of parasitic capacitance and resistance important for parasitic-aware design exploration before full physical implementation. However, progress on GNN-based parasitic modeling has been hindered by the lack of public, high-fidelity RC benchmarks that support reproducible evaluation. To address this gap, we introduce ParasGB, the first open-source benchmark suite for pre-layout parasitic parameter prediction on circuit graphs. ParasGB provides large-scale, heterogeneous RC networks extracted with commercial EDA tools from tape-out-proven designs, together with a unified evaluation protocol covering node-level ground capacitance, edge-level resistance, and edge-level coupling capacitance. Within this framework, we benchmark diverse GNN architectures using a standardized training pipeline and expose challenges such as extreme label imbalance, long-tailed parasitic distributions, and strong structural heterogeneity. By establishing a physically grounded and standardized benchmark for early-stage parasitic prediction, ParasGB provides an open platform for reproducible research on circuit graph learning and parasitic-aware model development. All datasets, preprocessing scripts, and configurations are publicly available in our code repository https://github.com/ShenShan123/ParasGB.git.

cs.LG↗
arXiv2026

A multi-band radio flux density catalog of ICRF3 sources using the Onsala Twin Telescopes

The VLBI Global Observing System (VGOS) is the next generation system for geodetic and astrometric Very Long Baseline Interferometry (VLBI). To optimize the observing time for each source in geodetic schedules, a flux density catalog is needed for the sources that are observed at the VGOS frequencies. The aim of this work is to monitor the flux densities of geodetic sources in the VGOS bands. The obtained flux density time series can be used for more effective scheduling of geodetic and astrometric VLBI experiments, as well as probing active galactic nuclei (AGN) physics. The Onsala Twin Telescopes have been used as a single baseline interferometer to measure flux densities of AGN that are part of the International Celestial Reference System (ICRF3). The telescopes observed at 3.2, 5.5, 6.6 and 10.4 GHz simultaneously. Both locally planned flux monitoring sessions and international geodetic experiments were analyzed. The data were calibrated using the Common Astronomy Software Applications (CASA). The possibility of predicting geodetic signal-to-noise ratios (S/N) using the measured flux densities was also tested. Simultaneous light curves in up to four frequencies have been obtained for 361 sources. The majority of the sources vary significantly in flux density during the measurement period. Most sources have a flat or inverted spectrum, with only 6 % having a steep spectrum. Furthermore, the flux densities from this work were shown to more precisely predict geodetic signal-to-noise ratios compared to the standard VGOS flux density catalog, especially for the most variable sources. Flux density variation needs to be taken into account to obtain the most optimal VGOS schedules. The flux density catalog presented here is expected to be of use for both astronomy and geodesy. We plan to continue the monitoring program.

astro-ph.IM↗
arXiv2026

I-Rex: An Interactive Debugger for SQL

SQL is declarative in nature and rich in its features. Writing semantically correct SQL queries and finding logical bugs in SQL are not easy, even for experienced programmers, who are often used to the mindset of working with general-purpose programming languages (GPLs). While there are many GPL debuggers, SQL debugging has received much less attention. In this paper, we present I-Rex, a SQL debugger that enables users to inspect the logical execution of SQL queries visually and interactively to identify and potentially fix logical bugs in the queries. I-Rex draws analogies to the debugging paradigm of GPLs (e.g., stepping, watchpoints, etc.), making it easier for programmers to adopt. However, unlike debugging GPLs, which involves executing the underlying program in full to the point of interest, I-Rex allows users to jump to arbitrary points of interest by leveraging the power of the database systems, through selective materialization and query rewrites. To simplify deployment, I-Rex acts as a lightweight middleware on top of the database system; it imposes no overhead to prepare a database for debugging and maintains no state in the database systems during debugging sessions. We demonstrate the effectiveness of I-Rex through performance experiments as well as a user study in an educational setting.

cs.DB↗
arXiv2026

UniSteer: Unified Noise Steering for Efficient Human-Guided VLA Adaptation

Diffusion-based vision-language-action (VLA) models have emerged as strong priors for robotic manipulation, yet adapting them to real-world distributions remains challenging. In particular, on-robot reinforcement learning (RL) is expensive and time-consuming, so effective adaptation depends on efficient policy improvement within a limited budget of real-world interactions. Noise-space RL lowers the cost by keeping the pretrained VLA fixed as a denoising generator while updating only a lightweight actor that predicts the noise. However, its performance is still limited due to inefficient autonomous exploration. Human corrective interventions can reduce this exploration burden, but they are naturally provided in action space, whereas noise-space finetuning requires supervision over noise variables. To address these challenges, we propose UniSteer, a Unified Noise Steering framework that combines human corrective guidance with noise-space RL through approximate action-to-noise inversion. Given a human corrective action, UniSteer inverts the frozen flow-matching decoder to recover a noise target, which provides supervised guidance for the same noise actor that is simultaneously optimized via reinforcement learning. Real-world experiments on diverse manipulation tasks show that UniSteer adapts more efficiently than strong noise-space RL and action-space human-in-the-loop baselines, improving the success rate from 20% to 90% in 66 minutes on average across four real-world adaptation tasks.

cs.RO↗
arXiv2026

Advancing Astrophysics with the SKA II

Advancing Astrophysics with the SKA II (AASKAII), written by our science community, outlines the transformative scientific advances that will be enabled by the SKA telescopes. In the decade since the publication of the previous edition, telescope designs have matured, construction has commenced, and the SKA Organisation has evolved into the SKA Observatory (SKAO). At the same time, observations from SKA precursor and pathfinder telescopes have provided new insights into longstanding scientific challenges while revealing entirely new phenomena. Published in advance of the first science verification campaign for the SKA Observatory, this volume looks ahead to the coming decades of discovery and innovation in radio astronomy. AASKAII spans the broad range of scientific research enabled by the SKA telescopes, SKA-Mid and SKA-Low. The contributions are organised into six thematic categories according to their scientific focus. The opening section presents overview chapters from the SKA Science Working Groups, around which our community is organised. Each overview provides the broader context that connects the contributions in this volume to the key scientific questions being pursued by their respective communities.

astro-ph.IM↗
arXiv2026

BaCon: Efficient Batch Processing of Counting Queries [Full Version]

Counting queries are ubiquitous in database systems, particularly for driving internal system optimization. Learned models for cardinality estimation rely heavily on large-scale training data, yet generating such data by executing massive batches of counting queries is expensive. We propose BaCon, an efficient algorithm for batch evaluation of counting queries on top of a database system, without modifying its internals. BaCon integrates the idea of factorized databases with a workload-aware domain quantization strategy, allowing it to evaluate batches of counting queries using compact data structures rather than materializing massive join results. BaCon's design is compatible with most database management system, and we have implemented it as a client-side application on PostgreSQL with a lightweight C-language UDF (user-defined function). This implementation delivers speedups between 2$\times$ and 178$\times$ over baselines and good performance across various workloads, making training and maintenance of learned cardinality estimation models significantly more practical.

cs.DB↗
arXiv2026

Beyond Monotonic Progress: Retry-Supervised Value Learning for Robot Imitation

Human demonstrations for robot imitation learning often contain mistakes and corrective behaviors, such as imprecise grasps, object misalignment, unstable contact, and repeated attempts. While these segments are commonly treated as noisy or suboptimal data, they provide valuable evidence about when execution deviates from a desirable path and how task feasibility can be restored. However, existing reward and value models often rely on monotonic progress assumptions, which capture coarse task advancement but may overlook local execution errors and corrective behaviors in imperfect demonstrations. In this work, we propose ReTVL (ReTry-Supervised Value Learning), a framework for learning mistake-sensitive value functions from mixed-quality robot demonstrations by leveraging retry events as sparse supervision. ReTVL captures the local degradation-and-recovery structure around mistakes by combining global progress calibration with local pairwise preference learning induced by sparsely annotated retry keypoints. The learned value model is then used to reweight demonstration chunks for downstream behavior cloning, reducing the influence of harmful execution errors while preserving useful corrective behaviors. Experiments on real-robot manipulation tasks show that ReTVL produces more fine-grained value estimates than progress-based baselines and improves imitation learning from imperfect demonstrations.

cs.RO↗
arXiv2026

UniSGR: Unified Framework for Semantic ID Generation and Ranking

Recommendation systems play a pivotal role in modern e-commerce platforms. While generative retrieval has emerged as a promising paradigm for alleviating the limitations of multi-stage cascade architectures, existing methods still struggle with fine-grained multi-objective ranking. To bridge this gap, we propose UniSGR, a Unified framework for Semantic ID Generation and Ranking. UniSGR adopts a two-stage training paradigm: a multi-scenario pre-training stage that learns from mixed business-scenario data, followed by a scenario-specific alignment stage that jointly optimizes Value-Aware Parallel Multi-Token Prediction (VA-PMTP) and a unified multi-objective ranking module. To better align generation with downstream ranking, we introduce Task-Aware Tokens (TAT) guided by Funnel-Aware Contrastive Learning. Furthermore, we propose Semantic Tree Attention with Reorganized KV cache (STARK), an inference strategy that removes key efficiency bottlenecks in conventional beam search. Extensive offline experiments on a large-scale e-commerce platform demonstrate the effectiveness and scalability of UniSGR.

cs.IR↗
arXiv2026

Estimating Velocity and Spin of Spherical Objects from Rolling-Shutter Image(s)

Rolling-shutter cameras introduce characteristic distortions when imaging fast moving objects, and these effects are typically treated as artifacts to be corrected. In this work, we instead leverage rolling-shutter distortions as a valuable source of temporal information to estimate the 3D translational and angular velocities of rapidly moving spherical objects from a single rolling-shutter frame. We design a robust and easily detectable spherical pattern and propose a correspondence-free formulation that recovers motion by enforcing geometric consistency in a back-projection framework. By exploiting the geometry of the sphere, translational and rotational motions are decoupled and estimated through a two-stage optimization process, enabling reliable velocity recovery even for textureless objects. Extensive experiments on both synthetic and real datasets demonstrate accurate and robust estimation of motion parameters under challenging high-speed conditions.

cs.CV↗
arXiv2026

Enhancing VLBI Capability with the SKA-Mid and the Jingdong 120-m Radio Telescope

The Jingdong Radio Telescope (JRT) is a 120-meter fully steerable radio telescope currently under construction in Jingdong County, Yunnan Province, China. Located at a relatively low latitude (24.5 degree), the JRT will enable observations of nearly 90% of the sky. Equipped with two broadband single-pixel receivers covering 1-8 GHz and 6-18 GHz, and a powerful digital backend, the telescope will support single-dish studies of various radio sources-particularly millisecond pulsars for enhancing the detection of nanohertz gravitational waves. In addition to single-dish capabilities, the JRT is expected to contribute approximately 800 hours annually to international Very Long Baseline Interferometry (VLBI) observations via a standard VLBI backend. When operating in conjunction with the phased-up SKA-Mid, the JRT will significantly enhance the technical and scientific capabilities of existing VLBI networks. This paper presents a comprehensive overview of the JRT's VLBI module and explores its potential to improve joint VLBI observations with current VLBI networks. Our analysis suggests that coordinated VLBI observations involving both the SKA-Mid and the JRT have the potential to significantly advance the field. For early sciences, we also highlight a few highly promising scientific cases, e.g. measuring the distance to PSR J0437-4715 with <1 ly accuracy and exploring jet formation with an event-horizon-scale resolution in M60*.

astro-ph.IM↗
arXiv2026

Mapping the Milky Way with Masers

SKA-VLBI is poised to revolutionize our understanding of the Galactic structure through its unprecedented astrometric precision and sensitivity. As a next-generation facility, it will answer long-standing questions about the Galactic structure by mapping its entire spiral structure in detail, spanning from the solar neighborhood, through the Galactic Center, to the far side of the Milky Way. Its access to the Southern sky will allow us to obtain more precise 3D parameters of the Galactic bar, reveal the nature of the 3-kpc Arm, and clarify the dynamical coupling between the bar and the spiral arms. By leveraging high-precision astrometry of numerous celestial objects with SKA-VLBI, the Galactic fundamental parameters such as the Solar motion and the Galactic rotation curve can be constrained more precisely. These advancements will not only elucidate the structure of our Milky Way, but also provide benchmarks for understanding barred spiral galaxies in general. Furthermore, they are important for advancing our knowledge of cosmological structure formation. The capabilities of SKA-VLBI will open a new era of high precision Galactic astrometry.

astro-ph.GA↗
arXiv2026

ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering

Knowledge-based Visual Question Answering (KB-VQA) requires models to combine image understanding with external knowledge. Most prior methods use a fixed retrieve-then-generate pipeline with a pre-selected retriever and a static top-k setting, which is not adaptive during reasoning. We propose ProMSA, a progressive multimodal search agent for KB-VQA. Given an image-question pair, the agent iteratively chooses image search, text search, or stop, under explicit tool-call budgets and with deduplication to avoid redundant retrieval. For training, we first use rejection-sampling SFT to learn valid tool-use formats, then optimize the agent with TN-GSPO, a sequence-level RL objective that normalizes updates by both generation length and tool-interaction depth. Experiments on E-VQA and InfoSeek show consistent gains over strong RAG and agent baselines, and improved retrieval and end-to-end accuracy. The code is available at https://github.com/DingWu1021/Promsa.

cs.CV↗
arXiv2026

Exploring Tidal Disruption Events with SKA and VLBI: Unveiling the Mystery of Black Hole Feeding and Outflows

Tidal disruption events (TDEs) probe the birth and evolution of black hole accretion flows and jets on human timescales. Radio emission traces shocks and outflows from thermal TDEs and powerful relativistic jets in the rare jetted class. SKA Mid, phased for VLBI and used together with global networks, will deliver milliarcsecond imaging, tens of microarcsecond astrometry, and microJy sensitivity, enabling: (i) proper motion measurements that discriminate off axis relativistic jets from subrelativistic winds; (ii) resolved morphologies and magnetic field diagnostics via polarimetry; and (iii) precise nuclear localization to distinguish SMBH vs. IMBH and to reveal recoiling or binary systems. SKA's wide frequency coverage (0.35 to 15.4 GHz) and 1h continuum sensitivities of 3 to 10 microJy per beam, together with multibeam tiedarray VLBI and a transient buffer for rapid triggers, are transformational. LSST, Einstein Probe, and SVOM will increase TDE alerts to hundreds per year, and late time radio flares appear common, ensuring rich SKA VLBI samples. We provide observing strategies, detection forecasts, and predictions, e.g., about 5 proper motion detections of jetted (or off axis) TDEs per year and routine core shift constraints at the microarcsecond level. This program will establish TDEs as laboratories for exploring jet launching, particle acceleration (including neutrinos), black hole accretion history and demographics, and properties of circumnuclear medium.

astro-ph.HE↗
arXiv2026

AGN Jets from Formation to Dissipation

Active Galactic Nuclei (AGN) are among the most energetic phenomena in the Universe, capable of launching powerful relativistic jets that extend from sub-parsec to megaparsec scales. These jets play a crucial role in regulating star formation, redistributing energy and matter, and shaping the evolution of galaxies and their environments. Despite decades of study, a comprehensive understanding of how AGN jets form, propagate, and dissipate remains elusive. The aim of this chapter is to highlight how the future capabilities of the the Square Kilometre Array (SKA), as a standalone array as well as in combination with Very Long Baseline Interferometry (VLBI) arrays and multi-wavelength facilities, will transform our capabilities to study the co-evolution of AGN jets and their host galaxies from jet formation to dissipation scales.

astro-ph.GA↗
arXiv2026

Augmented Roothaan-Hall Hessian Applied to Spin-Restricted Open-Shell Density-Functional Theory

We generalize the augmented Roothaan-Hall (ARH) Hessian formalism to the self-consistent field (SCF) optimization of spin-restricted open-shell (RO) wavefunctions, encompassing high-spin, low-spin, and two-determinant electronic states. A detailed ARH formulation is presented. We demonstrate that ARH is a highly efficient optimization algorithm for rapidly identifying accurate SCF minima, primarily owing to its systematic construction of an effective Hessian, particularly in the case of Euclidean quadratic energy functions. The ARH is built upon a universal energy formulation, including grid-based integration, for spin-restricted closed-shell, spin-unrestricted and RO density functional theory (DFT), thereby unifying and simplifying their numerical implementation. The performance of the present method is evaluated using two benchmarking studies. First, for a series of iron-sulfur clusters exhibiting different spin states, which represent notoriously challenging SCF problems, the ARH algorithm demonstrates superior convergence efficiency relative to L-BFGS and truncated Newton methods, requiring much fewer RO-SCF iterations to achieve convergence. Second, the ARH approach avoids convergence to higher-energy stationary points in two-determinant RO-SCF calculations for singlet excited states of selected photoactive compounds. Finally, an application of the ARH-based RO-SCF is illustrated by an investigation of the mechanistic origin of the spin-crossover phenomenon in Ni(II)-porphyrin complex utilized as a contrast agent.

physics.chem-ph↗