arXiv subjects

Xin Li

Publications and source records attributed to Xin Li.

At least 109 records · Page 6Linked to original sources

arXiv2026

LoViF 2026 The First Challenge on Unified Removal of Raindrops and Reflections: Methods and Results

This workshop paper comprehensively reviews the First Challenge on Unified Removal of Raindrops and Reflections. The challenge aims to address a frequently encountered practical problem in the field of autonomous driving, i.e., raindrop-reflection composite degradation on rainy days. This competition attracted 149 registered participants and received 12 valid final submissions with corresponding fact sheets, significantly contributing to the progress of unified removal of raindrops and reflections. All the methods are developed and evaluated on our real-shot RainDrop and ReFlection (RDRF) dataset. A detailed analysis of the submitted methods and corresponding results is provided in this report, which highlights effective approaches and provides interesting insights for future research.

cs.CV↗

arXiv2026

Persistent Homology as a Theory of Emergent Structure

Why do some macroscopic structures remain identifiable even though their microscopic constituents continually change? Vortices persist while fluid parcels turn over, neural memories persist while spikes and synapses fluctuate, and institutions persist while individuals enter and leave. We propose a scale-relative answer: an emergent property is a persistent nontrivial homology class [z]\in H_p=\ker\partial_p/\im\partial_{p+1}, a macro-feature that is closed but not exact across a filtration of descriptions. This identification turns emergence into a \emph{measurement} problem. Persistent bars detect stable macro-features, and we introduce a contractive-similarity (CS) graph operator to supply scaffold spectral gaps that predict robustness. Hodge decomposition separates harmonic macro-scaffold from exact and co-exact micro-flow; and functorial condensation explains when one level's emergent class becomes a unit for the next. The resulting scaffold-flow framework expresses six familiar signatures of emergence (i.e., inevitability, coherence, irreducibility, complementarity, robustness, and hierarchy) within one mathematical language. It also yields falsifiable predictions across atmospheric, neural, and social systems: genuine emergent structures should persist across filtrations, remain spectrally stable, respond disproportionately to harmonic interventions, and require timescale separation for hierarchical autonomy. We will also discuss the implications of structural persistence for AGI and ASI.

cs.LG↗

arXiv2026

RecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Space

Sparse-view 3D modeling represents a fundamental tension between reconstruction fidelity and generative plausibility. While feed-forward reconstruction excels in efficiency and input alignment, it often lacks the global priors needed for structural completeness. Conversely, diffusion-based generation provides rich geometric details but struggles with multi-view consistency. We present RecGen3D, a framework that combines these two paradigms into a cooperative system. To overcome inherent conflicts in coordinate spaces, 3D representations, and training objectives, we align both models within a shared canonical space. We employ decoupled cooperative learning, which maintains stable training while enabling seamless collaboration during inference. Specifically, the reconstruction module is adapted to provide canonical geometric anchors, while the diffusion generator leverages latent-augmented conditioning to refine and complete the geometric structure. Experimental results demonstrate that RecGen3D achieves superior fidelity and robustness, outperforming existing methods in creating complete and consistent 3D models from sparse observations.

cs.CV↗

arXiv2026

Substitution and quotient of the isotropy group action

Given a solution of the Brent equations, a partial solution can be substituted into the Brent equations which makes it a reduced polynomial system. Then the reduced polynomial system can be solved by symbolic software, and a parameterized solution set can often be found. However, the solution set admits a positive-dimensional isotropy group action. The parameterized solution set may lie entirely in a single isotropy group orbit. In this paper, we give a geometric explanation of making the substitution. Considering the foliation structure of the solution set, a method on choosing the partial solution is proposed. By the proposed method, parameterized solution sets that intersect distinct isotropy group orbits can be efficiently determined. In particular, the rational solution found by Dumas, Pernet and Sedoglavic is parameterized. In the parameterized solution set, we can find infinitely many inequivalent 48-multiplication algorithms with only rational coefficients.

math.AG↗

arXiv2026

MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement

Autoformalization is commonly framed as translating natural-language mathematical statements into machine-verifiable formal languages such as Lean 4. However, faithful formalization requires more than translation. Models must map mathematical concepts to the complex hierarchy of types and definitions in formal libraries such as Mathlib, while ensuring that generated statements preserve the meaning of the source propositions. Existing approaches struggle because they rely heavily on the model's parametric memory for library-specific knowledge, while common data construction pipelines often resort to filtering single-pass outputs and lack mechanisms for feedback-driven revision. To address these challenges, we introduce MathForm, an autoformalization framework for constructing verified training data through Mathlib knowledge retrieval and verification-guided iterative refinement. Before generation, a retrieval planner gathers relevant definitions and existing formalizations from Mathlib to guide the formalization generator. Generated statements are then revised using compiler diagnostics and semantic-consistency feedback. Using this framework, we construct FormalVerse, a Lean 4 dataset containing approximately 367K verified examples across diverse mathematical domains and sources. We then train MathForm-8B through supervised fine-tuning followed by reinforcement learning. Across six benchmarks, MathForm-8B achieves average Pass@8 rates of 88.06% under Syntax Check (SC) and 72.37% under Consistency Check (CC), outperforming multiple specialized 32B autoformalizers. On the challenging FATE-H and FATE-X subsets, it attains CC pass rates of 63% and 37%, exceeding the strongest specialized baselines in both cases.

cs.AI↗

arXiv2026

A Wandering 35,000-Solar-Mass Black Hole Fed by a Gravitational Wake

Intermediate-mass black holes are widely considered to be the seeds of supermassive black holes, a substantial population of which is expected to remain displaced from galactic nuclei owing to hierarchical galaxy assembly and inefficient dynamical friction. While several fueling channels can sustain central black holes, those pathways are largely inaccessible to off-nuclear black holes, leaving their fuel supply uncertain. As these wandering black holes move through the interstellar medium of their host galaxies, theory predicts that they can capture gas from the dense wake produced by gravitational focusing. However, direct observational evidence for this process has remained elusive. Here we report evidence for a wandering intermediate-mass black hole of 35,000 solar mass accreting through such a gravitational wake. Its black-hole nature is supported by broad-line emission, a compact continuum counterpart, long-term optical variability, and a power-law-like spectral energy distribution. Multi-epoch spectroscopy reveals three distinct gas components: a blueshifted, low-density upstream flow; a redshifted, dense downstream wake; and optically thick absorbers well within the capture radius that drive rapid changing-look variability in the broad-line emission. This discovery establishes a previously unobserved channel for the growth of wandering intermediate-mass black holes.

astro-ph.GA↗

arXiv2026

ConMem: Contribution-Aware Memory for Long-Horizon Manufacturing Inspection Logs

Long-horizon steel-equipment inspection requires reasoning over heterogeneous records accumulated across repeated inspection cycles. Existing retrieval-augmented generation systems treat historical logs as a static corpus and retain records without estimating their diagnostic value, failing to report early risk. To this end, we propose ConMem, a contribution-aware memory framework for LLM-assisted equipment inspection, supporting a human-in-the-loop early-risk screening system. Specifically, our ConMem first segments inspection logs into functional evidence units, then estimates each memory unit's contribution to downstream diagnosis through a Shapley-style estimation, and finally retains high-value evidence under a constrained memory budget. In experiments, we evaluate ConMem on real-world dataset and ConMem achieves 76.0% QA accuracy, exceeding the strongest directly comparable baseline. Relative to the naive 8K-context LLM baselines, it reduces the average number of input tokens by 88.2% and response time by 86.6%. Ablation studies also show that the functional-role-aware segmentation and contribution-based valuation are helping prioritize weak degradation signals for targeted field inspection. Practical deployments further confirm that ConMem retains the weak early signal across three inspection cycles, providing an early-stage seal-wear alert targeted for on-site inspectors.

cs.AI↗

arXiv2026

Bijectivity analysis of rational T-spline surfaces via Bernstein representations

Ensuring the bijectivity of spline-based parameterizations is fundamental in geometric modeling and isogeometric analysis, as invalid mappings may lead to self-intersections, singular Jacobians, and numerical instability. While T-splines offer enhanced flexibility through local refinement, this flexibility also makes bijectivity verification significantly more challenging. In this work, we propose a rigorous and efficient framework for bijectivity analysis of rational T-spline surfaces based on Bézier extraction. The key idea is to reformulate the T-spline representation into a collection of element-wise rational Bézier patches, on which the Gram determinant of the mapping admits a Bernstein polynomial representation. This enables a coefficient-based analysis of local regularity by exploiting the convex hull and positivity properties of the Bernstein basis. Based on this formulation, we derive a sufficient condition for bijectivity from the nonnegativity of Bernstein coefficients, together with a necessary condition based on the sign consistency of corner coefficients. For cases where these conditions are inconclusive, we introduce a hierarchical subdivision strategy that progressively localizes ambiguous regions and resolves them through refinement. The proposed method provides a certified and adaptive procedure for bijectivity verification that avoids dense numerical sampling and remains computationally efficient. Numerical experiments on complex T-spline geometries demonstrate that the approach accurately detects both valid and near-degenerate configurations, while scaling effectively to large models with thousands of rational Bézier patches. The framework is fully compatible with standard isogeometric analysis workflows.

math.NA↗

arXiv2026

MEC-Patch: Visible-Infrared Cross-Modal Adversarial Attack Driven by Intrinsic Material Emissivity Laws

With the widespread deployment of visible-infrared multimodal perception systems in safety-critical domains such as autonomous driving, evaluating their cross-modal adversarial robustness has become increasingly vital. However, existing approaches exhibit significant limitations in approximating the intrinsic laws of imaging. Most studies either focus on a single modality, failing to bypass cross-modal verification, or simplify infrared modeling into heuristic pixel-intensity distributions, neglecting the impact of ambient temperature fluctuations on adversarial stability. To bridge this gap, this paper proposes MEC-Patch, a cross-modal adversarial attack framework driven by intrinsic physical laws. By leveraging the Stefan-Boltzmann Law, we establish a physics-grounded cross-spectral mapping that explicitly links material emissivity to thermal radiation. Building on this formulation, we reveal that, under a fixed emissivity distribution, ambient temperature variations induce consistent global scaling while preserving relative emissivity-induced contrast. We exploit this property to construct temperature-robust adversarial perturbations whose discriminative patterns remain stable in the infrared modality, thereby fundamentally mitigating environmental sensitivity. Furthermore, we employ the physics-constrained NSGA-II algorithm to synergistically optimize the material-distribution-based patch parameters effective across both modalities, while enhancing generalization through a Dynamic Adversarial Resampling (DAR) strategy. Experimental results demonstrate that MEC-Patch effectively deceives state-of-the-art multimodal detectors and exhibits high robustness within high-fidelity, physically-consistent, and multi-scene simulation environments. This research provides a physical-law-driven perspective for the security assessment of multimodal perception systems.

cs.MM↗

arXiv2026

Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework

While retrieval-augmented generation systems partially address the hallucination issues in large language models, it also introduces new vulnerabilities to knowledge corruption attacks. Adversaries exploit these vulnerabilities by poisoning documents provided by RAG system to manipulate LLM outputs. To counter this threat, we propose SecureCollaRAG, a Byzantine-tolerant collaborative RAG framework leveraging Multi-source Knowledge Validation Mechanism. Our approach enables agent system to securely verify document provenance through dynamic GNN-based credibility scoring, effectively preventing stealthy knowledge corruption attacks while preserving essential domain knowledge integrity. Through extensive evaluations and formal analysis, we demonstrate that SecureCollaRAG maintains robustness against attackers under non-IID data distributions.

cs.CR↗

arXiv2026

LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment: Methods and Results

This paper reviews the LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment. This challenge aims to raise a new direction, i.e., how to evaluate the loss of semantic information from the human perspective, intending to promote the development of some new directions, like semantic coding, processing, and semantic-oriented optimization, etc. Unlike existing datasets of quality assessment, we form a dataset of human-oriented semantic quality assessment, termed the SeIQA dataset. This dataset is divided into three parts for this competition: (i) training data: 510 pairs of degraded images and their corresponding ground truth references; (ii) validation data: 80 pairs of degraded images and their corresponding ground-truth references; (iii) testing data: 160 pairs of degraded images and their corresponding ground-truth references. The primary objective of this challenge is to establish a new and powerful benchmark for human-oriented semantic image quality assessment. There are a total of 58 teams registered in this competition, and 6 teams submitted valid solutions and fact sheets for the final testing phase. These submissions achieved state-of-the-art (SOTA) performance on the SeIQA dataset.

cs.CV↗

arXiv2026

Effects of light-cluster degrees of freedom on collective flows in heavy-ion collisions at FOPI energies

Within a lattice Boltzmann-Uehling-Uhlenbeck transport model coupled to a kinetic approach for light-cluster formation, we investigate the impact of explicit light-cluster degrees of freedom on collective flows in Au+Au collisions at FOPI energies with beam energies $E_{\rm beam}$= $120$--$1500 A$ MeV by using a density-, momentum-, and isospin-dependent N$5$LO Skyrme pseudopotential. We first benchmark the kinetic approach by comparing the calculated light-cluster yields with FOPI data in central Au+Au collisions. We then analyze the collective flows of protons and light nuclei (deuterons, tritons, $^{3}\mathrm{He}$, and $^{4}\mathrm{He}$) in mid-central collisions. For protons, calculations with and without dynamical light-cluster degrees of freedom are compared to quantify the influence of dynamical cluster formation on proton directed ($v_1$), elliptic ($v_2$), triangular ($v_3$), and quadrangular ($v_4$) flows. We find that the dynamical light-cluster effect appreciably modifies proton $v_1$--$v_4$ flows at $E_{\rm beam}=120$--$150 A$ MeV, remains visible at $E_{\rm beam}=250$--$400 A$ MeV, and gradually weakens at $E_{\rm beam}\gtrsim 600 A$ MeV. For light nuclei, the kinetic approach captures the overall beam-energy dependence of the FOPI flow data, with better agreement for $E_{\rm beam}\geq 400 A$ MeV. We further examine the nucleon-number scaling of $v_2/A$ in both model calculations and experimental data, finding that the kinetic light-cluster formation approach qualitatively reproduces the observed scaling behavior. These results highlight the importance of a dynamical treatment of light-cluster formation for interpreting collective flows in heavy-ion collisions below about $600 A$ MeV, although the clustering effects on proton flows are minor at higher collision energies.

nucl-th↗

arXiv2026

Towards a new paradigm of scientific discovery with socialized artificial intelligence

Scientific discovery has advanced through successive transformations in the organization of knowledge. Observation and experimentation established the empirical foundations of science. Theory made it possible to derive general principles from particular phenomena. Computation extended inquiry into systems beyond direct observation, while data-intensive methods opened new spaces of pattern and prediction. Science now confronts a different frontier. The central challenge is no longer simply to produce more information, but to organize expanding knowledge, reasoning, and evidence into a coherent process of discovery. Here, we introduce Bridging Literature, Agents, and Zero-gap Experimentation (BLAZE), a paradigm of socialized scientific intelligence. BLAZE conceives AI not as an assistant for isolated research tasks, but as an organizational infrastructure for scientific discovery. It connects persistent knowledge, collective reasoning, empirical validation, and human judgment within a continuous research lifecycle, transforming fragmented activities into a cumulative process of inquiry, criticism, and revision. The central premise of BLAZE is that scientific intelligence does not arise from computation alone. It emerges from the sustained interaction among knowledge, hypotheses, experiments, and collective verification. By organizing humans and machines within a shared scientific process, BLAZE makes discovery more traceable, reproducible, and cumulative while preserving human creativity, judgment, and responsibility. Socialized scientific intelligence may provide a foundation for the next era of science. Its purpose is not to replace human discovery, but to extend the scale, depth, and continuity of collective scientific inquiry.

cs.AI↗

arXiv2026

What should we forget? A computational model of memory consolidation

Neural and immune memory rely on different biological mechanisms but face the same computational problem: future situations rarely repeat past ones exactly. Memory must retain distinctions that alter future responses while discarding irrelevant variation. We formulate this problem as \emph{scaffold-flow memory}: fast, state-dependent responses constitute the flow, whereas slowly changing physical variables form a scaffold that constrains future dynamics. Consolidation writes a predictive coarse-graining of experience into that scaffold. A useful coarse-graining must preserve future-relevant distinctions, generalize to novel experiences, support approximately autonomous coarse dynamics, and provide enough future benefit to justify its physical cost. We quantify failures of coarse autonomy through a leakage measure, relate leakage to excess future error, and identify persistent memory classes with slow dynamical modes. We further show that when experience does not self-average, storage is necessary rather than efficient. In a Willshaw associative memory, a metastable neural attractor, and a stochastic affinity-maturation model, future risk is minimized at an intermediate granularity: overly fine representations waste capacity and generalize poorly, whereas overly coarse ones merge situations requiring different responses. These results support a common computational principle: \emph{memory consolidation selects a predictive, dynamically usable, and affordable representation of the past}.

q-bio.NC↗

arXiv2026

CoT-Edit: Let CoT Guide Instruction Video Editing

Text-driven instruction-based video editing in complex scenes remains challenging: purely textual prompts often fail to capture precise spatial relationships and physical constraints, resulting in target ambiguity and physically implausible outcomes. To address this, we propose a plan--guide--edit framework that explicitly bridges semantic intent and spatial execution. In our framework, a Chain-of-Thought (CoT)-enhanced multimodal large language model (MLLM) serves as a planner, performing structured reasoning over the video and instructions to derive a precise sequence of bounding boxes and attribute-enriched editing directives. These spatial priors then guide a box-conditioned mask generator, transforming ambiguous global retrieval into localized, context-aware refinement and producing masks that more accurately capture object scale, contact relationships, and placement. Building on these spatial and semantic signals, a diffusion-based editor integrates the masks, enriched instructions, and frame features to render high-fidelity edits that remain temporally coherent and spatially well aligned. Trained first in a modular manner and then jointly, our framework achieves superior performance with reduced data requirements, delivering precise localization in scenes with multiple similar objects and physically consistent object additions, and extensive experiments demonstrate state-of-the-art performance over multiple strong baseline methods. More details are available at: https://github.com/flying-sky999/CoT-Edit

cs.CV↗

arXiv2026

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model

We present RynnBrain 1.1, a family of embodied foundation models spanning 2B, 9B, and 122B-A10B scales. Trained with a unified spatio-temporal and physically grounded framework, RynnBrain 1.1 supports embodied perception, spatial reasoning, localization, and planning. Compared with RynnBrain 1.0, it further introduces contact-point prediction across the model family and native 3D grounding for the 2B and 9B models, yielding representations and outputs that are more directly aligned with robot manipulation. We also develop RynnBrain-VLA with a unified cross-embodiment action space and embodiment-specific masking, and deploy it on Unitree G1, Astribot-S1, and Tianji-Wuji. RynnBrain 1.1 achieves strong results on embodied cognition, localization, and 3D grounding, with the 122B-A10B model outperforming all evaluated proprietary and open-source models on VSI-Bench, MMSI, and RefSpatial-Bench. Real-robot experiments show that RynnBrain-initialized policies outperform Qwen-based and representative generalist VLAs, while joint multi-task and multi-embodiment training improves process scores and success rates over per-task training.

cs.RO↗

arXiv2026

ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency

Vision-language-action (VLA) policies achieve strong performance in robotic manipulation but remain vulnerable to runtime disturbances that break the temporal alignment among visual observations, robot states, and executed actions. We introduce ActFovea, a plug-and-play safeguarding framework that detects and mitigates such failures without retraining or modifying the underlying VLA policy. ActFovea uses robot kinematics, proprioceptive states, and recent actions to construct action-conditioned foveated regions that retain contact-relevant areas and predicted motion corridors while suppressing task-irrelevant visual content. It detects runtime risks by evaluating whether visual motion and observation freshness remain consistent with geometric, proprioceptive, and action transitions. For recoverable disturbances, ActFovea constructs disturbance-specific candidate observations and accepts a recovery only after verifying the resulting action chunk. When stale or replayed observations make reliable recovery impossible, it invokes a bounded safe-failure procedure. In closed-loop evaluations of $π_0$ across multiple LIBERO suites, ActFovea increases success under localized visual overlays from 49.3\% to 90.3\%, closing 93.7\% of the gap to clean performance. It further improves success under action drift and visual delay by 7.0 and 9.8 percentage points, respectively, while preserving clean-task performance. Under frozen-observation replay, ActFovea triggers timely safe failure in all trials, with no unprotected failures. These results demonstrate that spatiotemporal visual-action consistency provides an effective basis for runtime safeguarding of VLA policies.

cs.RO↗

arXiv2026

StanceFlip: A Comprehensive Multi-Dimensional Benchmark for Multimodal Conversational Stance Flipping Forecasting

Conversational stance detection has shifted from static text analysis to dynamic multimodal modeling. However, existing benchmarks exhibit three key limitations: failure to capture the dynamic evolution of beliefs, particularly during stance reversals; difficulty in disentangling affective states from logical reasoning; and neglect of the critical role of multimodal cues in resolving pragmatic ambiguities such as sarcasm. To address these limitations, we propose StanceFlip, a benchmark designed for multimodal conversational stance flipping forecasting over multi-turn dialogues across five modalities and multi-scenarios, which includes two novel subtasks: 1) Multimodal Stance Sextuple Extraction, extracting holder, target, emotion, sentiment, stance, and rationale as static state snapshots of dialogue to capture fine-grained cognitive structures. 2) Dynamic Stance Flip Attribution, tracking stance reversals across the conversation and identifying their underlying triggers. Alongside the dataset, we propose a dedicated framework, named ConStaFF, for Multimodal Conversational Stance Flipping Forecasting (MCSFF). Built upon a large language model, ConStaFF performs end-to-end stance reasoning, with a Thought-of-Stance (ToS) reasoning framework and a self-reflective verification mechanism integrated for structured stance modeling and faithful flip attribution. Specifically, ToS decomposes the reasoning process into specialized cognitive personas to formulate target propositions, resolve cross-modal conflicts, and infer historical stance trajectories. Extensive experiments show that our approach achieves state-of-the-art performance on both sextuple extraction and flip-trigger attribution, outperforming strong multimodal large language model baselines by substantial margins.

cs.CL↗