arXiv subjects

Xingyu Zhu

Publications and source records attributed to Xingyu Zhu.

At least 37 records · Page 2Linked to original sources

arXiv2026

Dual-Route Top-K Retrieval with 1v1 VLM Reranking for the CoVR-R

We describe \emph{Dual-Route Top-K Retrieval with 1v1 VLM Reranking} for the CoVR-R challenge. The method treats composed video retrieval as two coupled problems: finding a sufficiently complete top-k candidate set, and then safely deciding whether any candidate should replace a strong current top-1. We first improve the reasoning/text seed with a VLM slot selector over existing candidates, without introducing DFN visual retrieval. We then add a visual route from contact-sheet embeddings using DFN-H/DFN-L. The routes are merged into a top-10 candidate set, after which a VLM final reranker performs conservative 1v1 comparisons between the current top-1 and each challenger. On the hidden test split, the final system reaches 95.28 R@1, 97.47 R@5, 98.48 R@10, and 99.66 R@50. The main lesson is that CoVR-R benefits more from recall-selection decoupling than from broad text reranking or direct multi-candidate VLM classification.

cs.CV↗

arXiv2026

Adaptive Dense Evidence Refinement for Video Relational Reasoning for VRR-QA Challenge

VRR-QA evaluates whether video-language systems can infer spatial, temporal, viewpoint, depth, and visibility relations that are not always resolved by a single frame. We present an inference-only system built around adaptive test-time computation. The system first answers each question with a direct video-language model pass, then uses multiple lightweight views to find unstable questions. Only these difficult questions are routed to a high-budget dense evidence module that constructs timestamped frame observations, relation-specific probes, candidate verification, and conservative temporal aggregation. This design separates two problems that are often confused in video question answering: finding plausible alternative answers and deciding when a current answer should actually be changed. On the test split, the final system obtains 90.07 average accuracy and 87.81 macro average accuracy. The report focuses on the final test system and the implementation settings required to reproduce the adaptive dense verifier.

cs.CV↗

arXiv2026

Temporal Evidence Routing with Structured Visual Evidence for TimeLogicQA

TimeLogicQA evaluates whether video question answering systems can reason over temporal relations such as event existence, ordering, persistence, boundary conditions, and overlap. We address this task with a visual evidence routing pipeline that separates perception from symbolic temporal reasoning. The system first parses each question into event targets, answer mode, candidate options, and temporal operators. It then routes videos according to duration and operator difficulty, using ordered full-frame evidence for short clips and event-focused candidate windows for long videos. A multimodal large language model produces structured visual evidence for the relevant events, while programmatic verifiers recover dense action intervals and a deterministic reducer applies operator-specific temporal rules to produce the final answer. Conservative fusion accepts an answer only when the visual evidence, temporal program, and confidence checks agree, reducing noisy answer flips. On the official test evaluation, our final system achieves an AvgAcc of 81.8.

cs.CV↗

arXiv2026

Nonnegative Ricci Curvature and Uniformly Convex Boundary Forces Compactness

We confirm a compactness conjecture of M. Li. If a complete Riemannian manifold has nonnegative Ricci curvature and uniformly convex boundary in the sense that the second fundamental form satisfies $h\ge1$. Then we prove it is compact, and consequently has finite fundamental group. The proof uses monotone quantities constructed via positive proper harmonic functions with Neumann condition.

math.DG↗

arXiv2026

TCP-MCP: Landscape-Guided Co-Evolution of Prompts and Communication Topologies for Multi-Agent Systems

Effective multi-agent systems cannot be designed by selecting prompts or communication graphs in isolation. Agent behavior depends on the information an agent receives, while the usefulness of a communication edge depends on how the receiving agent interprets and uses that information. We propose \textbf{TCP-MCP} (Topology-Coupled Prompting for Multi-Agent Collaborative Problem-Solving), a co-evolution framework that searches agent prompts and communication topologies as a unified genome. TCP-MCP uses an initialization-time landscape probe to calibrate early search behavior, and then relies on Pareto-front diagnostics to adapt exploration under three objectives: task performance, token cost, and structural complexity. Using the same DeepSeek-V3.2 backbone across all methods, TCP-MCP achieves 82.66\%, 89.96\%, and 96.61\% accuracy on MMLU-Pro, MMLU, and GSM8K, respectively. Across the three benchmarks, it consistently outperforms automated graph-generation baselines and achieves competitive accuracy relative to debate-style systems, while using up to 5.69$\times$ fewer tokens than those systems at the reported operating points. These results show that jointly evolving prompts and communication structure provides a practical route to cost-aware and task-adaptive multi-agent system design in controlled evaluations.

cs.AI↗

arXiv2026

Fibrations, the First Betti Number, and Almost Nonnegative Ricci Curvature

In this paper, we prove fibration theorems for manifolds with almost nonnegative Ricci curvature and certain extra regularity assumptions. We show that a closed $n$-manifold $M$ satisfying $\mathrm{diam}(M)^2\mathrm{sec}_M \geq -κ$ and $\mathrm{diam}(M)^2\mathrm{Ric}_M \geq -δ$, where $δ>0$ is sufficiently small depending only on $n$ and $κ$, fibers over a $b_1(M)$-torus. This removes the upper sectional curvature bound required in the earlier result of Yamaguchi \cite{Y88}. As a corollary, we obtain a refinement of Yamaguchi's smooth fibration theorem (\cite{Y91}), showing that the fiber itself (rather than a finite cover of it) fibers over a $b_1$-torus. Our results extend to manifolds satisfying a generalized Reifenberg condition introduced in \cite{HH24}, which encompasses both a lower bound on sectional curvature and the local rewinding Reifenberg condition. In the nonsmooth setting, a similar result also holds for a non-collapsed $\mathrm{RCD}(-ε(D,r,n),n)$ space whose diameter is bounded by $D$ and which satisfies the $(r,δ(n))$-local rewinding Reifenberg condition. The proofs rely on an equivariant regularity theorem for almost submetries under a lower Ricci curvature bound. In addition, we study the stability of rank of Abelian actions along equivariant Gromov-Hausdorff convergence in this paper.

math.DG↗

arXiv2026

Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control

Safety alignment of large language models remains brittle under domain shift and noisy preference supervision. Most existing robust alignment methods focus on uncertainty in alignment data, while overlooking optimization-induced fragility in preference-based objectives. In this work, we revisit robustness for LLM safety alignment from an optimization geometry perspective, and argue that robustness failures cannot be addressed by data-centric methods alone. We propose \textit{ShaPO}, a geometry-aware preference optimization framework that enforces worst-case alignment objectives via selective geometry control over alignment-critical parameter subspace. By avoiding uniform geometry constraints, ShaPO mitigates the over-regularization that can harm robustness under distribution shift. We instantiate ShaPO at two levels: token-level ShaPO stabilizes likelihood-based surrogate optimization, while reward-level ShaPO enforces reward-consistent optimization under noisy supervision. Across diverse safety benchmarks and noisy preference settings, ShaPO consistently improves safety robustness over popular preference optimization methods. Moreover, ShaPO composes cleanly with data-robust objectives, yielding additional gains and empirically supporting the proposed optimization-geometry perspective. The code is available at https://github.com/liujilong0116/ShaPO.

cs.LG↗

arXiv2026

Asymptotic-Type Dimension Bounds through Combinatorial Approaches

We develop a probabilistic framework for large-scale dimension bounds in metric geometry, based on padded decompositions, randomized ball carving on net graphs, and the Lovász Local Lemma. For metric measure spaces with volume doubling constant $C_{\mathsf D}$, we prove the sharp bound $\mathrm{asdim}_{AN}(X)\le \mathrm{dim}_{AN}(X)\le \lfloor{\log_2 C_{\mathsf D}}\rfloor$. In particular, if $(M,g)$ is a complete Riemannian $n$-manifold with $\mathrm{Ric}_g\ge 0$, then $\mathrm{asdim}(M)\le n$, thereby settling a question of Papasoglu on manifolds with nonnegative Ricci curvature. We also show that if $(X,\mathsf{d},\mathfrak{m})$ is proper, volume noncollapsed, and has polynomial volume growth rate $ρ^V(X)$, then $\mathrm{asdim}(X)\le \lfloor{ρ^V(X)}\rfloor$. Moreover, the corresponding control function can be chosen to have polynomial growth. This extends Papasoglu's sharp asymptotic-dimension bound from graphs of polynomial growth to a metric-measure setting. As applications, we study equality in the polynomial-growth bound for universal covers of nilmanifolds, and under nonnegative Ricci curvature we relate the equality case in the volume-doubling bound to Gromov largeness, obtaining in particular a consequence for complete manifolds with positive scalar curvature.

math.MG↗

arXiv2026

Search for quasar pairs with Gaia astrometric data. II. Photometric redshift prediction with machine learning for the MGQPC catalogue

The identification of physically associated kiloparsec-scale quasar pairs is important for understanding galaxy evolution, the growth of supermassive black holes, and their co-evolution with host galaxies. However, their rarity and the high contamination from stellar superpositions and projected alignments require efficient pre-selection methods. We develop a machine-learning framework to produce photometric-redshift point estimates and redshift probability density functions for quasars, with the main goal of identifying high-probability quasar pair candidates in the MGQPC catalogue. We construct two large spectroscopically confirmed quasar samples with multi-wavelength photometry, based on SDSS and DESI Legacy Imaging Surveys data. CatBoost is used for point-estimate photometric-redshift regression, and FlexZBoost is used for full redshift-PDF estimation. The workflow achieves robust performance, with a normalised median absolute deviation of 0.036 and an outlier fraction of 5.6% on the test sample. Applying the trained model to the MGQPC catalogue, we identify 185 high-probability quasar pair candidates based on photometric-redshift consistency. Among them, 20 systems have been subsequently confirmed as genuine physical pairs by independent spectroscopic observations. The resulting MGQPC photometric-redshift catalogue provides a useful resource for future spectroscopic follow-up of quasar pairs and dual supermassive black holes.

astro-ph.GA↗

arXiv2026

Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation

Large Vision-Language Models (LVLMs) exhibit powerful generative capabilities but frequently produce hallucinations that compromise output reliability. Fine-tuning on annotated data devoid of hallucinations offers the most direct solution, while its high computational cost motivates recent representation-based methods, which focus on mitigating hallucinatory components within hidden representations. Though efficient, we empirically observe that these methods degrade general generation capacity due to incomplete extraction of hallucination components and non-selective parameter updates. To address these limitations, we propose MPD, a dual-stage framework for mitigating hallucinations without performance degradation. Specifically, our MPD relies on two essential factors: (1) semantic-aware component disentanglement to extract pure hallucination components, and (2) interpretable parameter updates that selectively modify parameters most relevant to hallucination. Extensive experiments demonstrate that MPD achieves state-of-the-art performance, reducing hallucinations by 23.4\% while maintaining 97.4\% of general generative capability as evaluated on LLaVA-Bench and MME, with no additional computational cost.

cs.CV↗

arXiv2026

Complete manifolds with nonnegative Ricci curvature and slow relative volume growth

For any complete and noncompact manifold $M$ with $\mathrm{Ric}\ge 0$, we define a function $\mathrm{RV}(s)$ that describes the growth of relative volume asymptotically $$\mathrm{RV}(s)=\limsup_{r\to\infty} \dfrac{\mathrm{vol} B_{rs}(p)}{\mathrm{vol} B_r(p)},\quad s\ge 1.$$ Then we study the fundamental groups of such manifolds with slow relative volume growth and sublinear diameter growth. We show that if $\mathrm{RV}(s)\ll s^2$ as $s\to\infty$, then $π_1(M)$ is almost abelian; if $\mathrm{RV}(s)\ll s^{1+δ}$ for some $δ\in (0,1)$ and the Ricci curvature is positive at a point, then $π_1(M)$ is finite. These results generalize our previous work on complete manifolds with $\mathrm{Ric}\ge 0$ and linear (minimal) volume growth.

math.DG↗

arXiv2026

Topology of 3-manifolds with nonnegative scalar curvature and positive harmonic functions

We study complete $3$-manifolds with nonnegative scalar curvature under additional regularity assumptions. We prove that a contractible such manifold is diffeomorphic to $\mathbb{R}^3$, and that an open handlebody admitting such a metric must have genus at most $1$. The proof uses exhaustions by level sets of harmonic functions and refined average gradient estimates.

math.DG↗

arXiv2026

Proton Temperature Anisotropy Across Interplanetary Shocks: A Statistical Analysis with WIND observations

Interplanetary (IP) shocks efficiently modify the proton temperature anisotropy of the solar wind. Analyzing ~800 IP shocks observed by the Wind spacecraft from 1997-2024, we present a statistical study of upstream and downstream proton temperature anisotropy and its dependence on shock geometry, compression, and distance from the shock. We find that (1) quasi-perpendicular shocks produce a pronounced enhancement of perpendicular temperature downstream (Tperp > Tpara), whereas parallel shocks remain near isotropic downstream due to typically stronger upstream Tpara; (2) comparisons with the Chew-Goldberger-Low (CGL) double-adiabatic model reveal geometry-dependent deviations. CGL overestimates downstream perpendicular heating and underestimates parallel heating at quasi-perpendicular shocks, with the opposite trend at quasi-parallel shocks, highlighting the importance of non-adiabatic processes beyond simple compression; (3) Shock-driven anisotropy is strongly localized near the shock and gradually relaxes toward typical solar wind conditions farther downstream as the shock's influence diminishes; and (4) downstream anisotropy is regulated by kinetic instabilities, with quasi-perpendicular shocks constrained by proton cyclotron and mirror instabilities and quasi-parallel shocks limited by the parallel firehose instability. Together, these results show that the evolution of temperature anisotropy at interplanetary shocks is controlled by shock geometry, localized processes, and instability driven regulation.

physics.space-ph↗

arXiv2026

Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learning

Multimodal 3D vision-language models show strong generalization across diverse 3D tasks, but their performance still degrades notably under domain shifts. This has motivated recent studies on test-time adaptation (TTA), which enables models to adapt online using test-time data. Among existing TTA methods, cache-based mechanisms are widely adopted for leveraging previously observed samples in online prediction refinement. However, they store only limited historical information, leading to progressive information loss as the test stream evolves. In addition, their prediction logits are fused heuristically, making adaptation unstable. To address these limitations, we propose BayesMM, a Multimodal Bayesian Distribution Learning framework for test-time point cloud analysis. BayesMM models textual priors and streaming visual features of each class as Gaussian distributions: textual parameters are derived from semantic prompts, while visual parameters are updated online with arriving samples. The two modalities are fused via Bayesian model averaging, which automatically adjusts their contributions based on posterior evidence, yielding a unified prediction that adapts continually to evolving test-time data without training. Extensive experiments on multiple point cloud benchmarks demonstrate that BayesMM maintains robustness under distributional shifts, yielding over 4% average improvement.

cs.CV↗

arXiv2026

Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models

As vision-language models (VLMs) are increasingly deployed in open-world scenarios, they can be easily induced by visual jailbreak attacks to generate harmful content, posing serious risks to model safety and trustworthy usage. Recent activation steering methods inject directional vectors into model activations during inference to induce refusal behaviors and have demonstrated effectiveness. However, a steering vector may both enhance refusal ability and cause over-refusal, thereby degrading model performance on benign inputs. Moreover, due to the lack of theoretical interpretability, these methods still suffer from limited robustness and effectiveness. To better balance safety and utility, we propose NullSteer, a null-space projected activation defense framework. Our method constructs refusal directions within model activations through a linear transformation: it maintains zero perturbation within the benign subspace while dynamically inducing refusal along potentially harmful directions, thereby theoretically achieving safety enhancement without impairing the model's general capabilities. Extensive experiments show that NullSteer significantly reduces harmful outputs under various jailbreak attacks (average ASR reduction over 15 percent on MiniGPT-4) while maintaining comparable performance to the original model on general benchmarks.

cs.CV↗

arXiv2026

Multimodal OCR: Parse Anything from Documents

We present Multimodal OCR (MOCR), a document parsing paradigm that jointly parses text and graphics into unified textual representations. Unlike conventional OCR systems that focus on text recognition and leave graphical regions as cropped pixels, our method, termed dots.mocr, treats visual elements such as charts, diagrams, tables, and icons as first-class parsing targets, enabling systems to parse documents while preserving semantic relationships across elements. It offers several advantages: (1) it reconstructs both text and graphics as structured outputs, enabling more faithful document reconstruction; (2) it supports end-to-end training over heterogeneous document elements, allowing models to exploit semantic relations between textual and visual components; and (3) it converts previously discarded graphics into reusable code-level supervision, unlocking multimodal supervision embedded in existing documents. To make this paradigm practical at scale, we build a comprehensive data engine from PDFs, rendered webpages, and native SVG assets, and train a compact 3B-parameter model through staged pretraining and supervised fine-tuning. We evaluate dots.mocr from two perspectives: document parsing and structured graphics parsing. On document parsing benchmarks, it ranks second only to Gemini 3 Pro on our OCR Arena Elo leaderboard, surpasses existing open-source document parsing systems, and sets a new state of the art of 83.9 on olmOCR Bench. On structured graphics parsing, our model achieves higher reconstruction quality than Gemini 3 Pro across image-to-SVG benchmarks, demonstrating strong performance on charts, UI layouts, scientific figures, and chemical diagrams. These results show a scalable path toward building large-scale image-to-code corpora for multimodal pretraining. Code and models are publicly available at https://github.com/rednote-hilab/dots.mocr.

cs.CV↗

arXiv2026

Search for Quasar Pairs with ${\it Gaia}$ Astrometric Data. I. Method and Candidates

Quasar pairs, a special subclass of galaxy pairs, are valuable in the investigation of quasar interaction, clustering, co-evolution between the two quasars' host galaxies, the growth of supermassive black holes, as well as the formation and evolution of galaxies. However, quasar pairs on kpc scales are observationally rare. The scarcity of available samples hindered the deeper exploration and statistics of these objects. In this work, we apply an astrometric method to systematically search for quasar candidates within a transverse distance of 100 kpc to known quasars in the Million Quasar Catalog. These candidates are \textit{Gaia} sources with proper motions and parallaxes that are consistent with zero. Visual inspection of the sample was performed to remove the contamination of crowded stellar fields and nearby galaxies. A total of 4\,112 quasar pair candidates were isolated, with a median member separation of 8.81{\arcsec}, a median \textit{Gaia} $G$-band magnitude of 20.52, and a median redshift of 1.61. Our catalog was compared with three major candidate quasar pair catalogs and identified 3\,984 new quasar pair candidates previously uncataloged in the three catalogs. Several interesting quasar pair candidates are highlighted and discussed. We also briefly discussed our quasar selection and several techniques for improving the success rate of quasar pair selection. Extensive spectroscopic follow-up campaigns are being carried out to validate their astrophysical nature.

astro-ph.GA↗

arXiv2026

A Quasar Pair Sample Compiled from DESI DR1

Interacting quasar pairs (QPs, either dual or binary) provide crucial insights into galaxy mergers, black hole growth, and large-scale structure formation. The current literature reports fewer than 200 spectroscopically confirmed QPs, highlighting the need for larger samples to enable statistically meaningful investigations. In this paper, we present a sample of 1,220 quasar pairs or candidates compiled from the DESI DR1 quasar sample. Among them, 145 systems have been previously reported. We visually classified the full sample using DESI Legacy Images and SPARCL spectra into three categories: QP (quasar pairs, N = 1020), QPC (quasar pair candidates, N = 142), LQC (lensed quasar candidates, N = 58). Within the LQC subset, we find an intriguing wide-separation ($\sim$7.15$^{\prime\prime}$) quadruply lensed quasar candidate. The redshift distribution of pair sample peaks at $z \sim 1$--$2.5$, with an overall pair fraction of $6.2^{+0.2}_{-0.2}\times10^{-4}$ (Poisson error) and a generally weak redshift dependence. 63.8\% of QPs have $|ΔV_r| < 600$\,km/s, suggesting dynamical associations. This sample offers a statistically meaningful dataset for future studies of quasar pairs, lensing events, and potentially merger-triggered or merger-induced SMBH growth across the merger sequence.

astro-ph.GA↗