arXiv subjects

Xinyu Dai

Publications and source records attributed to Xinyu Dai.

At least 19 recordsLinked to original sources

arXiv2026

Dark Matter and MOND successes and degeneracies in reproducing SPARC rotation curves and weak lensing data

The observed rotation velocities of spiral galaxies at large scales exceed those predicted by their baryonic components, motivating the need for dark matter (DM) or Modified Newtonian Dynamics (MOND). We fit the rotation curves of 147 late-type galaxies from the SPARC database, using a suite of models including Cold Dark Matter (CDM) models with and without baryonic feedback, Warm DM, Fuzzy DM, and MOND. We also combine SPARC kinematics with weak-lensing data to extend the mean rotation curves to ~1 Mpc. On a galaxy-by-galaxy basis, the inner SPARC rotation curves marginally favour CDM models with baryonic feedback, although accounting for the uncertainties in distances and inclinations increases the degeneracy among DM-based models and MOND. All DM models predict host halo masses larger than abundance-matching expectations, with only the CDM model with baryonic feedback reducing the scatter around the mean luminosity-halo mass relation. MOND is able to reproduce the flatness of the mean galactic rotation curves on scales up to 1 Mpc, providing stellar mass-to-light ratios within observational uncertainties. In contrast, all DM models, without the contribution of mass external to the bound halo, struggle to explain the flat rotation curves. The inclusion of the current weak-lensing data tends to favour MOND over DM models, at least at the largest scales. Future observations from BIG-SPARC, the Square Kilometre Array, and most importantly, upcoming weak-lensing surveys such as EUCLID and Rubin will provide more stringent and independent tests of these competing frameworks

astro-ph.GA↗

arXiv2026

Harness Policy Distillation: Aligning Agent Policies with Runtime Semantics

Deploying a general-purpose model as an agent means running it inside a product-specific runtime harness that decides which actions are executable, how state advances, and when the loop may terminate. Ordinary trajectory supervision shows which action was taken but leaves the runtime semantics behind that action implicit. We introduce Harness Policy Distillation (HPD), which makes these runtime control semantics an explicit training target alongside actions to align the harness policy. HPD replays reference trajectories through the harness to recover the runtime semantics that are implicit in ordinary trajectory data, and represents them as control documents at each model-call boundary. These documents provide privileged information for a teacher to generate actions, while harness verification ensures that the resulting targets are executable under the runtime contract. We jointly train a shared model on the runtime semantics recovered from control-state privileged information and native history, thereby internalizing these semantics into the model policy. At deployment, the trained model uses the original harness interface without requiring the control document or any additional supplement. On TRAJECT-Bench with the Pi harness, Qwen3-8B trained with HPD reaches 22.98% autonomous task success and 49.23% runtime compliance, against 3.09% and 19.90% for the unadapted model. Harness-verified teacher actions substantially improve the native deployment policy, while joint control-state supervision provides further gains in task completion and runtime compliance. HPD turns executable runtime semantics into dense supervision for learning harness-compatible actions at each decision boundary.

cs.LG↗

arXiv2026

Perfect matchings in planar 3-connected graphs: girth five and minimum degree five

Let $Φ(G)$ denote the number of perfect matchings of a graph $G$. Goedgebeur et al. posted two questions about the perfect matchings of planar 3-connected graphs: does there exist an infinite family of matchable planar 3-connected graphs of girth 5 with a constant number of perfect matchings? Whether there exist infinitely many planar 3-connected graphs with minimum degree 5 which have a constant number of perfect matchings. We present answers to those questions. First, we construct, for every even $n\ge196$, a simple planar 3-connected graph of order $n$ and girth five with exactly $c$ perfect matchings, where $c$ is a fixed positive integer. Second, for a simple planar 3-connected graph $G$ with a perfect matching and minimum degree at least five, we show that $Φ(G)\ge2^{\lceil(|V(G)|+20)/22\rceil}$. This implies that, for each positive integer $t$, only finitely many such graphs, up to isomorphism, have at most $t$ perfect matchings.

math.CO↗

arXiv2026

The Nineteenth Data Release of the Sloan Digital Sky Survey

Mapping the local and distant Universe is key to our understanding of it. For decades, the Sloan Digital Sky Survey (SDSS) has made a concerted effort to map millions of celestial objects to constrain the physical processes that govern our Universe. The most recent and fifth generation of SDSS (SDSS-V) is organized into three scientific ``mappers". Milky Way Mapper (MWM) that aims to chart the various components of the Milky Way and constrain its formation and assembly, Black Hole Mapper (BHM), which focuses on understanding supermassive black holes in distant galaxies across the Universe, and Local Volume Mapper (LVM), which uses integral field spectroscopy to map the ionized interstellar medium in the local group. This paper describes and outlines the scope and content for the nineteenth data release (DR19) of SDSS and the most substantial to date in SDSS-V. DR19 is the first to contain data from all three mappers. Additionally, we also describe nine value added catalogs (VACs) that enhance the science that can be conducted with the SDSS-V data. Finally, we discuss how to access SDSS DR19 and provide illustrative examples and tutorials.

astro-ph.GA↗

arXiv2026

OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools

We introduce OpenMobile-2, a near-frontier mobile agent with fully open training environments and recipes. We make three key advances: (1) Diverse environments with simulated commercial apps: We build MobileGym++, featuring 35 realistic, functionally rich commercial-style apps with cross-app workflows, while preserving full controllability for reset and verification. Together with newly configured apps in Android emulators, this yields a diverse playground spanning over 110 apps. (2) Open training data at scale: Building on this foundation, we curate nearly 12K mobile interaction trajectories for supervised fine-tuning and the largest open collection of verifiable RL training data for mobile agents, comprising over 2K executable tasks with automatic rewards. (3) Hybrid GUI and app-native tool use: We explore an experimental mobile-use setting where apps expose selected functionalities as app-native tools alongside their GUIs, allowing agents to interleave GUI actions and tool calls within a task. We implement this setting in MobileGym++ with over 300 carefully scoped tools across 50+ apps. Additionally, we introduce MobileGym++ Bench for complex, long-horizon commercial mobile scenarios, supporting both GUI-only and hybrid GUI-tool evaluation on a shared task suite. OpenMobile-2 performs competitively across established benchmarks, including AndroidWorld (79.9) and MobileWorld (50.4), while showing promising transfer to real-device mobile use, nearly doubling SPA-Bench performance from 31.9 to 59.6. All resources are available at https://os-copilot.github.io/OpenMobile2-Home/.

cs.SE↗

arXiv2026

A Gravitationally Lensed Low-Luminosity AGN From The Cosmic Noon

Strong gravitational lensing provides a unique tool of studying intrinsically faint high-redshift active galactic nuclei (AGN). In particular, low-luminosity AGN (LLAGN) can probe black-hole growth in low-mass galaxies that current X-ray surveys cannot otherwise access. We investigate the nature and physical properties of a faint X-ray source triply imaged by the galaxy cluster SDSS J2243$-$0935, and determine whether the source hosts an AGN. We combine archival Hubble Space Telescope imaging and Chandra X-ray observations with the published strong-lensing models of SDSS J2243$-$0935. We constrain the source redshift geometrically, derive magnification maps, and infer the physical properties of the host galaxy. The geometric lensing analysis gives a source redshift of $z=2.14^{+0.12}_{-0.17}$, consistent with the photometric redshift estimate, and a total magnification of $μ=78\pm7$. The source is triply lensed and detected only in the HST F160W band, with an intrinsic magnitude of $m_{\rm AB}=28.2\pm0.2$. The rest-frame optical emission implies a stellar mass of $8.6\lesssim\log(M_\star/M_\odot)\lesssim9.4$. The unobscured star formation rate is constrained to $\mathrm{SFR}_{\rm UV}<0.009\,M_\odot\,\mathrm{yr}^{-1}$, although substantial dust obscuration remains possible. Chandra detects X-ray point-source counterparts to all three HST-detected lensed images. The combined X-ray spectrum contains $100\pm11$ net counts and is consistent with a moderately absorbed power law, with $Γ\simeq 1.48$ and $N_{\rm H}=(5.5\pm4.4)\times10^{22}\,\mathrm{cm}^{-2}$. After correcting for gravitational magnification, we obtain an intrinsic rest-frame $2$--$10$ keV luminosity of $L_{\rm X}=1.2\pm0.3\times10^{42}\,\mathrm{erg\,s^{-1}}$. The X-ray emission is likely dominated by an AGN hosted by a low-mass galaxy at $z\simeq2.14$, making this system a strongly lensed LLAGN at cosmic noon (abridged).

astro-ph.GA↗

arXiv2026

WebNavigator: Global Web Navigation via Interaction Graph Retrieval

Despite significant advances in autonomous web navigation, current methods remain far from human-level performance in complex web environments. We argue that this limitation stems from Topological Blindness, where agents are forced to explore via trial-and-error without access to the global topological structure of the environment. To overcome this limitation, we introduce WebNavigator, which reframes web navigation from probabilistic exploration into deterministic retrieval and pathfinding. WebNavigator constructs Interaction Graphs via zero-token cost heuristic exploration offline and implements a Retrieve-Reason-Teleport workflow for global navigation online. WebNavigator achieves state-of-the-art performance on WebArena and OnlineMind2Web. On WebArena multi-site tasks, WebNavigator achieves a 72.9\% success rate, more than doubling the performance of enterprise-level agents. This work reveals that Topological Blindness, rather than model reasoning capabilities alone, is an underestimated bottleneck in autonomous web navigation.

cs.IR↗

arXiv2026

Neutralizing Popularity Bias in LLM-based Recommendation via Counterfactual Reasoning Guidelines

In the era of generative AI, recommender systems are moving from precise prediction to trustworthy generation. Large language models (LLMs) support this shift by inferring user interests and producing natural-language explanations. However, LLM-based recommendation suffers from a fundamental obstacle: popularity bias. Through pre-training on massive corpora, LLMs tend to rely on global statistics and trend signals, yielding recommendations that follow popularity rather than genuine preference. As this bias is entangled in model parameters and is hard to remove directly, we propose Neutralizing Popularity Bias in LLM-based Recommendation via Counterfactual Reasoning Guidelines (NPRec), a model-agnostic framework that mitigates popularity bias through external semantic intervention. NPRec performs counterfactual refinement to causally separate intrinsic user interests from popularity-driven conformity, producing debiased textual guidelines that reflect actual user preferences. These guidelines are injected at inference time to shift the LLM from unconstrained generation to guided reasoning, without any parameter updates. Serving as explicit premises, they both ground faithful explanations and improve recommendation quality. Extensive experiments on three real-world datasets demonstrate that NPRec achieves promising performance in recommendation accuracy, explanation quality, and debiasing capability.

cs.AI↗

arXiv2026

Bricks in which every vertex is incident with a forcing edge

A matching covered graph is a brick if it is 3-connected and bicritical. An edge of a matching covered graph G is a forcing edge if it lies in precisely one perfect matching of G. We prove that every vertex of a simple brick G is incident with a forcing edge if and only if G is an odd wheel or is isomorphic to one of the following three graphs: the triangular prism \overline{C_6},\overline{C_6}^+ or the bicorn H_8. Here \overline{C_6}^+ is obtained from \overline{C_6} by adding an edge between two nonadjacent vertices.

math.CO↗

arXiv2026

Is Multimodal Speculative Decoding Ready for Diffusion-Based Parallel Drafting? A Survey and Empirical Diagnosis

Speculative decoding accelerates autoregressive generation by allowing a lightweight drafter to propose future tokens while a target model verifies them in parallel. Its lossless guarantee has motivated a line of work that pushes the drafter itself toward parallel generation. The most recent paradigm is block-parallel generative drafting, including diffusion-based methods such as DFlash and DSpark, achieving up to 3.6x speedup on common daily chatting tasks. While this transition is well studied in text-only LLMs, its applicability to multimodal models remains an open question. Existing multimodal speculative decoding efforts focus on input compression, adapter alignment, candidate coverage, or modality-specific verification; however, block-parallel generative drafting remains largely unexplored. To bridge this gap, this paper combines a modality-centered survey with a cross-architecture empirical study to ask: Is multimodal speculative decoding ready for diffusion-based parallel drafting? In this survey, we systematically analyze a wide spectrum of multimodal models, spanning Vision-Language, Video-Language, Audio, and Vision-Language-Action (VLA) architectures, from the dual perspectives of drafting parallelism and cross-modal information interaction. We introduce a unified taxonomy that isolates drafter-side parallelism from orthogonal design choices such as tree construction and verification strategies. Furthermore, we provide a comprehensive empirical comparison of existing methods under varying degrees of parallelism across standardized multimodal benchmarks, including OCR, VQA, visual reasoning, and image captioning. Finally, we summarize the limitations of current approaches, discuss open challenges, and outline promising future directions for this rapidly evolving field.

cs.AI↗

arXiv2026

The X-Ray Continuum Emission Region in the Lensed Quasar SDSS J133907.23+131038.6 is Much Smaller than the Accretion Disk

We analyze microlensing variability in 15 seasons of optical monitoring data and 4 epochs of new X-ray observations of the doubly-imaged gravitationally lensed quasar SDSS J133907.23+131038.6 to place empirical constraints on the size and structure of that system's X-ray and optical continuum emission regions. Employing a Bayesian Monte Carlo method, we analyzed ground-based optical light curves to constrain the half-light radius of the far-UV source $\log(r_{\rm 1/2, FUV}/{\rm cm})=15.78^{+0.26}_{-0.28}$ at 193 nm, the rest-frame center of the {\it r}-band, assuming a $60^\circ$ inclination angle. This size corresponds to $\sim100\,{\it r}_{\rm g}$ for a $4.0 \times 10^{8} \: {\rm M_{\odot}}$ black hole. We measured the half-light radius of the full band ($0.2-8.0 \: {\rm keV}$) X-ray continuum emission region $\log(r_{\rm 1/2, X_{full}}/{\rm cm})=14.32^{+0.23}_{-0.31}$, a size measurement that is consistent with the radius of the innermost stable circular orbit (ISCO) in the Schwarzschild metric.Two shifted Fe K$α$ lines caused by microlensing are detected in the stacked spectrum of image A at 5.9 and 8.9~keV at $>99\%$ significance.

astro-ph.HE↗

arXiv2026

OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories

Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding. The prevailing recipe learns this capability from teacher-generated trajectories filtered for answer correctness, implicitly assuming that every successful demonstration provides effective supervision. We argue this assumption is flawed: a strong teacher often reaches the correct answer without needing its tool calls, and imitating such trajectories teaches a student that tool calls accompany correct answers, not that tool observations ground them. We present OpenVisTool, an open framework for constructing instructive visual tool-use trajectories that provide effective supervision for tool learning. The key insight is that a trajectory should be retained only if its answer is correct (outcome validity) and its tool observations causally contribute to that answer (causal utility). The framework operates in three stages: difficulty screening to select queries that are not reliably answerable without tools, domain-specific trajectory synthesis to elicit coherent tool-use trajectories, and supervision verification to jointly test both conditions. Rather than encouraging models to imitate tool calls, the resulting supervision teaches when and how visual evidence should be acquired. Using this framework, we construct OpenVisTool-42K, a dataset spanning five visual reasoning domains, together with OpenVisTool-Bench, a benchmark covering the same domains. Across four backbones (4B-27B), fine-tuning on OpenVisTool-42K consistently improves visual tool-use performance and yields gains on two out-of-distribution benchmarks; the larger models approach leading closed-source systems. The evidence suggests that effective visual tool use is learned from causally grounded supervision rather than tool-calling patterns.

cs.CL↗

arXiv2026

MultiModal Code-Switching: Interleaving Visual Objects into Language for Explicit Object-Level Alignment

Existing Multimodal Large Language Models (MLLMs) predominantly rely on image-text pairs for modality alignment pretraining, mapping global image representations to long textual descriptions. However, this image-level alignment suffers from referential ambiguity: models struggle to infer the correspondences between multiple visual objects and textual entities from the global representation, leading to data inefficiency and suboptimal semantic grounding. To address this, we propose MultiModal Code-Switching (MMCS), a novel pretraining paradigm that provides explicit object-level supervision. Inspired by the linguistic phenomenon of code-switching, MMCS interleaves vision and language by replacing textual entities with their corresponding visual objects, enforcing local vision-language grounding. We further develop a scalable data synthesis pipeline to generate a pretraining dataset of 773K samples with accurate object-entity correspondences. Experiments show that MMCS is highly data-efficient: with only 50K samples, it matches or surpasses models trained on 600K image-text pairs. Furthermore, MMCS consistently improves visual grounding and perception capabilities across varying model scales.

cs.CV↗

arXiv2026

The number of perfect matchings in 3-connected planar graphs

A graph is matchable if it admits a perfect matching. Recently, Goedgebeur et al. asked whether there exists a constant $c<12$ such that infinitely many matchable planar $3$-connected graphs, each with exactly $c$ perfect matchings. We answer this question by proving that every matchable planar $3$-connected graph on at least 40 vertices has at least 12 perfect matchings, and this lower bound is sharp.

math.CO↗

arXiv2026

The Twentieth Data Release of the Sloan Digital Sky Survey: First All-Sky BOSS Spectra, eROSITA-SDSS-V Mapper Coordinated Observations, and a Preview of the Local Volume Mapper

This paper presents the twentieth data release (DR20) from the Sloan Digital Sky Survey, the third data release of its fifth generation (SDSS-V). SDSS-V is a panoptic spectroscopy survey that is mapping the stars, gas, and galaxies through three scientific programs: the Milky Way Mapper (MWM), the Local Volume Mapper (LVM), and the Black Hole Mapper (BHM). DR20 presents the first optical (BOSS) SDSS-V spectra from southern hemisphere for the MWM and BHM surveys; new optical MWM and BHM data from the northern hemisphere are also available, for a total over 3 million spectra of 1.5 million stars and half a million galaxies and quasars, with galactic and extragalactic x-ray targets coordinate with eROSITA DR2. DR20 includes integral field spectroscopy maps from LVM of six targets and 169 tiles, spanning Galactic HII regions, planetary nebulae, and nearby galaxies. Additionally, eighteen value added catalogs are also released with DR20, based on SDSS-V MWM and BHM data, and we present a new LVM visualization tool including an RGB HiPS map as a value added product.

astro-ph.GA↗

arXiv2026

Spectroscopic Analysis of Fermi-detected Blazars using SDSS-V

The automated spectroscopic pipeline of the Sloan Digital Sky Survey (SDSS) systematically assigns Galactic star, galaxy, or typical quasar classifications to jet-dominated blazars, owing to the absence of a non-thermal jet continuum component in its template library. In this study, we present a new, physically motivated, multi-component spectral fitting pipeline that we apply to 746 optical counterparts of Fermi/4FGL-DR4 $γ$-ray sources in the SDSS-V Data Release 20 spectroscopic database, yielding 707 well-fitted blazar candidates dominated by Power-law+Galaxy (59.4%), Power-law+Lines (22.6%), and Power-law+QSO (15.0%) model families. Independent WISE infrared (IR) photometry confirms that 96.6% of the 88 sources originally misclassified as Galactic stars by SDSS fall within the canonical blazar region, with 90.9% reclassified as BL Lacertae object (BL Lac) candidates, demonstrating the success of our new pipeline. The new classification scheme naturally recovers the known cosmological separation between BL Lac and Flat Spectrum Radio Quasar (FSRQ) candidates and a separation of approximately one order of magnitude in median $γ$-ray luminosity. We compare our redshift estimates to a validation sample of 111 sources in the Third Fermi-LAT Catalogue of High-Energy Sources (3FHL), finding a 10.4% reduction in catastrophic failures ($η= 0.387$ vs 0.432) over the SDSS pipeline. The equivalent width analysis validates the traditional |EW| = 5 Ang classification boundary at the population level (BL Lac: 4.47 $\pm$ 0.15 Ang; FSRQ: 22.86 $\pm$ 0.86 Ang), although 49.5% of individual BL Lac candidates exceed this threshold and 51.4% show simultaneous emission and absorption features. This hybrid population challenges the traditional binary blazar classification and points towards a more physically continuous description of blazar properties.

astro-ph.HE↗

arXiv2026

Dynamic Decision-Making under Model Misspecification: A Stochastic Stability Approach

Dynamic decision-making under model uncertainty is central to many economic environments, yet existing bandit and reinforcement learning algorithms rely on the assumption of correct model specification. This paper studies the behavior and performance of one of the most commonly used Bayesian reinforcement learning algorithms, Thompson Sampling (TS), when the model class is misspecified. We first provide a complete dynamic classification of posterior evolution in a misspecified two-armed Gaussian bandit, identifying distinct regimes: correct model concentration, incorrect model concentration, and persistent belief mixing, characterized by the direction of statistical evidence and the model-action mapping. These regimes yield sharp predictions for limiting beliefs, action frequencies, and asymptotic regret. We then extend the analysis to a general finite model class and develop a unified stochastic stability framework that represents posterior evolution as a Markov process on the belief simplex. This approach characterizes two sufficient conditions to classify the ergodic and transient behaviors and provides inductive dimensional reductions of the posterior dynamics. Our results offer the first qualitative and geometric classification of TS under misspecification, bridging Bayesian learning with evolutionary dynamics, and also build the foundations of robust decision-making in structured bandits.

econ.TH↗

arXiv2026

Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning

Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation. However, current reranking models are typically optimized on static human annotated relevance labels in isolation, decoupled from the downstream generation process. This isolation leads to a fundamental misalignment: documents identified as topically relevant by information retrieval metrics often fail to provide the actual utility required by the LLM for precise answer generation. To bridge this gap, we introduce ReRanking Preference Optimization (RRPO), a reinforcement learning framework that directly aligns reranking with the LLM's generation quality. By formulating reranking as a sequential decision-making process, RRPO optimizes for context utility using LLM feedback, thereby eliminating the need for expensive human annotations. To ensure training stability, we further introduce a reference-anchored deterministic baseline. Extensive experiments on knowledge-intensive benchmarks demonstrate that RRPO significantly outperforms strong baselines, including the powerful list-wise reranker RankZephyr. Further analysis highlights the versatility of our framework: it generalizes seamlessly to diverse readers (e.g., GPT-4o), integrates orthogonally with query expansion modules like Query2Doc, and remains robust even when trained with noisy supervisors.

cs.CL↗