arXiv subjects

Rui Xu

Publications and source records attributed to Rui Xu.

At least 55 records · Page 3Linked to original sources

arXiv2026

Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed across the open web; models therefore need to jointly perform cross-frame clue extraction, iterative retrieval, and multi-hop reasoning-based verification. To bridge this gap, we construct the first video deep research benchmark, VideoDR. VideoDR centers on video-conditioned open-domain video question answering, requiring cross-frame visual anchor extraction, interactive web retrieval, and multi-hop reasoning over joint video-web evidence; through rigorous human annotation and quality control, we obtain high-quality video deep research samples spanning six semantic domains. We evaluate multiple closed-source and open-source multimodal large language models under both the Workflow and Agentic paradigms, and the results show that Agentic is not consistently superior to Workflow: its gains depend on a model's ability to maintain the initial video anchors over long retrieval chains. Further analysis indicates that goal drift and long-horizon consistency are the core bottlenecks. In sum, VideoDR provides a systematic benchmark for studying video agents in open-web settings and reveals the key challenges for next-generation video deep research agents.

cs.CV↗

arXiv2026

Performance Analysis of Single-Antenna Fluid Antenna Systems via Extreme Value Theory

In single-antenna fluid antenna systems (FASs), the transceiver dynamically selects the antenna port with the strongest instantaneous channel to enhance link reliability. However, deriving accurate yet tractable performance expressions under fully correlated fading remains challenging, primarily due to the absence of a closed-form distribution for the FAS channel. To address this gap, this paper develops a novel performance evaluation framework for FAS operating under fully correlated Rayleigh fading, by modeling the FAS channel through extreme value distributions (EVDs). We first justify the suitability of EVD modeling and approximate the FAS channel through the Gumbel distribution, with parameters expressed as functions of the number of ports and the antenna aperture size via the maximum likelihood (ML) criterion. Closed-form expressions for the outage probability (OP) and ergodic capacity (EC) are then derived. While the Gumbel model provides an excellent fit, minor deviations arise in the extreme-probability regions. To further improve accuracy, we extend the framework using the generalized extreme value (GEV) distribution and obtain closed-form OP and EC approximations based on ML-derived parameters. Simulation results confirm that the proposed GEV-based framework achieves superior accuracy over the Gumbel-based model, while both EVD-based approaches offer computationally efficient and analytically tractable tools for evaluating the performance of FAS under realistic correlated fading conditions.

cs.IT↗

arXiv2026

Formulation of testing gravitational redshift based on Laser Time link between China Space Station and a ground station

This paper presents a high-precision gravitational redshift test using the China Space Station (CSS) Laser Time Transfer (CLT) system. We develop a comprehensive observation equation based on a c^{-3} order relativistic model for space-ground clock comparison. While the CSS optical clock system is currently in the orbital debugging phase, our simulation using actual CSS orbit data achieves a gravitational redshift verification precision of (1.8 \pm 47)*10^{-7} -- approximately one order of magnitude improvement over previous experiments. Our work represents the first application of laser-based time transfer for gravitational redshift verification at such precision, and the first use of the CSS CLT link for testing this fundamental aspect of General Relativity. Unlike microwave-based methods, our laser approach avoids ionospheric effects and first-order Doppler shifts. Residual analysis identifies tropospheric delay variations and atmospheric turbulence as the primary remaining uncertainty contributors. The achieved precision enables gravitational potential difference measurements with 0.1 m^2/s^2 precision -- offering new capabilities for both fundamental physics investigations and geodetic applications including intercontinental height transfer. This work establishes a new benchmark for high-precision tests of relativistic physics and demonstrates the transformative potential of space-based optical time transfer.

gr-qc↗

arXiv2026

Sculpting Spin-Wave Landscapes via Curvature of 2D Magnonic Crystals

Engineering the dispersion relation is one of the key ingredients enabling the application of spin waves in computational elements. One way to engineer the spin-wave band structure is to create an artificial magnonic crystal, which can be used to design specific band gaps or dispersion branches. However, creating a two-dimensional magnonic crystal usually requires removing material, which dramatically decreases the decay lengths of spin waves. Here, we present a method to manipulate the demagnetizing field landscape by utilizing large-area curvilinear nanotemplates consisting of three-dimensional nanopyramids arranged in a square lattice with a period of 400 nm. In a 50-nm-thick Permalloy film grown on these curvilinear templates, we experimentally observe a complete in-plane band gap together with flat-band modes that exhibit strong real-space localization of the spin waves in the pyramid valleys. Micro-focused Brillouin light scattering measurements corroborate the numerically predicted dispersion and reveal the possibility of opening and closing this gap by varying the external magnetic field. Our results establish three-dimensional-templated continuous films as a versatile platform for two-dimensional signal processing and magnonic computing elements.

cond-mat.mes-hall↗

arXiv2026

SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors

Gaussian Splatting demonstrates impressive results in multi-view reconstruction based on Gaussian explicit representations. However, the current Gaussian primitives only have a single view-dependent color and an opacity to represent the appearance and geometry of the scene, resulting in a non-compact representation. In this paper, we introduce a new method called SVGS (Spatially Varying Gaussian Splatting) that utilizes spatially varying colors and opacity in a single Gaussian primitive to improve its representation ability. We have implemented bilinear interpolation, movable kernels, and tiny neural networks as spatially varying functions. SVGS employs 2D Gaussian surfels as primitives, which significantly enhances novel-view synthesis while maintaining high-quality geometric reconstruction. This approach is particularly effective in practical applications, as scenes combining complex textures with relatively simple geometry occur frequently in real-world environments. Quantitative and qualitative experimental results demonstrate that all three functions outperform the baseline, with the best movable kernels achieving superior novel view synthesis performance on multiple datasets, highlighting the strong potential of spatially varying functions. Project page: https://ruixu.me/html/SuperGaussians/index.html

cs.CV↗

arXiv2026

Robust Conditional Conformal Prediction via Branched Normalizing Flow

Conformal prediction (CP) constructs prediction sets with marginal coverage guarantees under the assumption that the calibration and test distributions are identical. However, under distribution shift, existing approaches primarily align marginal conformal score distributions, which is sufficient to preserve marginal coverage but does not control the conditional coverage error at individual test inputs. As a consequence, CP can remain unreliable in regions where the conditional score distributions are mismatched. In this work, we bound the conditional invalidity of CP under distribution shift in terms of the Wasserstein distance between the calibration and test distributions. This result highlights the role of invertible transport in mitigating conditional coverage degradation. Motivated by this insight, we introduce Branched Normalizing Flow (BNF), a two-branch architecture that normalizes a test input to the calibration distribution and transforms the prediction set of the normalized input back to the test distribution while preserving conditional guarantees. Empirically, BNF consistently improves conditional coverage robustness on nine datasets across a wide range of confidence levels.

cs.LG↗

arXiv2026

Strips as Tokens: Artist Mesh Generation with Native UV Segmentation

Recent advancements in autoregressive transformers have demonstrated remarkable potential for generating artist-quality meshes. However, the token ordering strategies employed by existing methods typically fail to meet professional artist standards, where coordinate-based sorting yields inefficiently long sequences, and patch-based heuristics disrupt the continuous edge flow and structural regularity essential for high-quality modeling. To address these limitations, we propose Strips as Tokens (SATO), a novel framework with a token ordering strategy inspired by triangle strips. By constructing the sequence as a connected chain of faces that explicitly encodes UV boundaries, our method naturally preserves the organized edge flow and semantic layout characteristic of artist-created meshes. A key advantage of this formulation is its unified representation, enabling the same token sequence to be decoded into either a triangle or quadrilateral mesh. This flexibility facilitates joint training on both data types: large-scale triangle data provides fundamental structural priors, while high-quality quad data enhances the geometric regularity of the outputs. Extensive experiments demonstrate that SATO consistently outperforms prior methods in terms of geometric quality, structural coherence, and UV segmentation. Project page: https://ruixu.me/html/SATO/index.html

cs.CV↗

arXiv2026

Geometry-Calibrated Conformal Abstention for Language Models

When language models lack relevant knowledge for a given query, they frequently generate plausible responses that can be hallucinations, rather than admitting being agnostic about the answer. Retraining models to reward admitting ignorance can lead to overly conservative behaviors and poor generalization due to scarce evaluation benchmarks. We propose a post hoc framework, Conformal Abstention (CA), adapted from conformal prediction (CP) to determine whether to abstain from answering a query. CA provides finite-sample guarantees on both the probability of participation (i.e., not abstaining) and the probability that the generated response is correct. Importantly, the abstention decision relies on prediction confidence rather than the non-conformity scores used in CP, which are intractable for open-ended generation. To better align prediction confidence with the model's ignorance, we introduce a calibration strategy using representation geometry within the model to measure knowledge involvement in shaping the response. Experiments demonstrate that we improve selective answering significantly with 75 percent conditional correctness.

cs.CL↗

arXiv2026

ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models

In this paper, we study an under-explored but important factor of diffusion generative models, i.e., the combinatorial complexity. Data samples are generally high-dimensional, and for various structured generation tasks, additional attributes are combined to associate with data samples. We show that the space spanned by the combination of dimensions and attributes can be insufficiently covered by existing training schemes of diffusion generative models, potentially limiting test time performance. We present a simple fix to this problem by constructing stochastic processes that fully exploit the combinatorial structures, hence the name ComboStoc. Using this simple strategy, we show that network training is significantly accelerated across diverse data modalities, including images and 3D structured shapes. Moreover, ComboStoc enables a new way of test time generation which uses asynchronous time steps for different dimensions and attributes, thus allowing for varying degrees of control over them. Our code is available at: https://github.com/Xrvitd/ComboStoc

cs.LG↗

arXiv2026

HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing

LLM role-playing, i.e., using LLMs to simulate specific personas, has emerged as a key capability in various applications, such as companionship, content creation and digital games. While current models effectively capture character tones and knowledge, simulating the inner thoughts behind their behaviors remains a challenge. Towards cognitive simulation in LLM role-play, previous efforts mainly suffer from two deficiencies: lacking data with high-quality reasoning traces, and lacking reliable reward signals aligned with human preferences. In this paper, we propose HER, a unified framework for cognitive-level persona simulation. HER introduces dual-layer thinking, which distinguishes characters' first-person thinking from LLMs' third-person thinking. To bridge these gaps, we curate reasoning-augmented role-playing data via reverse engineering, and construct human-aligned principles and reward models. Leveraging these resources, we train HER models based on Qwen3-32B via supervised and reinforcement learning. Extensive experiments validate the effectiveness of our approach. Notably, our models significantly outperform the Qwen3-32B baseline, achieving a 30.26 improvement on the CoSER benchmark and a 14.97% gain on the Minimax Role-Play Bench. Our datasets, principles, and models are released to facilitate future research.

cs.LG↗

arXiv2026

Chip-Scale Aligned Chiral Carbon Nanotubes Exhibiting Giant Second Harmonic Generation

Chiral carbon nanotubes (CNTs) are direct-gap semiconductors with optical properties governed by one-dimensional excitons with enormous oscillator strengths. Each species of chiral CNTs has an enantiomeric pair of left- and right-handed CNTs with nearly identical properties, but enantiomer-dependent phenomena can emerge, especially in nonlinear optical processes. Theoretical studies have predicted strong second-order nonlinearities in chiral CNTs, but no experimental quantitative verification has been reported due to the lack of macroscopically ordered assemblies of single-enantiomer chiral CNTs. Here, we report the synthesis of centimeter-scale, densely packed, aligned single-enantiomer chiral CNT films that are microfabrication-compatible. We observe giant second harmonic generation (SHG) emission from the chiral CNT film, which originates from the intrinsic chirality and inversion symmetry breaking of the atomic structure of chiral CNTs. The observed nonlinear susceptibility of the as-fabricated film reaches $4.9\times 10^2$\,pm/V at a pump wavelength of 1030\,nm, corresponding to the lowest-energy excitonic resonance, indicating $χ_{xyz} = 1.6\times 10^3$\,pm/V for a perfectly aligned CNT crystal. Our calculations based on many-body theory correctly estimate the spectrum and magnitude of such excitonically enhanced optical nonlinearity. These results are promising for the development of scalable chiral-CNT electronics and nonlinear photonics.

physics.app-ph↗

arXiv2026

CLASP: Training-Free LLM-Assisted Source Code Watermarking via Semantic-Preserving Transformations

The proliferation of open-source code and large language models (LLMs) for code generation has amplified the risks of unauthorized reuse and intellectual property infringement. Source code watermarking offers a potential solution, yet existing methods typically encode watermarks through identifiers, local code patterns, or limited handcrafted edits, leaving them vulnerable to renaming, refactoring, and adaptive watermark removal. These limitations hinder the joint achievement of robustness, capacity, generalization, and deployment efficiency. We propose CLASP, a Code LLM-Assisted Semantic-Preserving watermarking framework that enables training-free, plug-and-play watermarking for source code. CLASP embeds watermark bits within a fixed space of semantics-preserving transformations, enabling automated watermark insertion with higher capacity while remaining reusable across programming languages and less dependent on brittle lexical features. To recover the watermark, CLASP uses reference-code retrieval and differential comparison to identify transformation traces, avoiding task-specific model training while improving robustness to structural edits and adaptive attacks. Experiments across multiple programming languages show that CLASP consistently outperforms existing baselines in watermark extraction accuracy and robustness, while maintaining code quality under both random removal and adaptive de-watermarking attacks.

cs.CR↗

arXiv2026

Uncertainty Quantification on Graph Learning: A Survey

Graphical models have demonstrated their exceptional capabilities across numerous applications. However, their performance, confidence, and trustworthiness are often limited by the inherent randomness in data generation and the lack of knowledge to accurately model real-world complexities. There has been increased interest in developing uncertainty quantification (UQ) techniques tailored to graphical models. In this survey, we systematically examine existing works on UQ for graphical models. This survey distinguishes itself from most existing UQ surveys by specifically concentrating on graphical models, including graph neural networks and graph foundation models. We organize the literature along two complementary dimensions: uncertainty representation and uncertainty handling. By synthesizing both established methodologies and emerging trends, we aim to bridge gaps in understanding key challenges and opportunities in UQ for graphical models, inspiring researchers on graphical models or uncertainty quantification to make further advancements at the cross of the two fields.

cs.LG↗

arXiv2026

The stealth Kerr solution in the bumblebee gravity

In this paper, we find Kerr solution accompanied with a nontrivial vector field as a solution to one of the simplest vector-tensor theories of gravity, namely the bumblebee model with an intriguing coupling constant between the Ricci curvature tensor and the vector field. We also demonstrate that the accompanied vector field can be generated via the Newman-Janis algorithm from a simple spherical vector field, which together with the Schwarzschild metric constitutes a solution to the same bumblebee model. It is probably the simplest example of a theory and its black-hole solutions for the Newman-Janis algorithm to hold except for general relativity.

gr-qc↗

arXiv2026

InterveneBench: Benchmarking LLMs for Intervention Reasoning and Causal Study Design in Real Social Systems

Causal inference in social science relies on end-to-end, intervention-centered research-design reasoning grounded in real-world policy interventions, but current benchmarks fail to evaluate this capability of large language models (LLMs). We present InterveneBench, a benchmark designed to assess such reasoning in realistic social settings. Each instance in InterveneBench is derived from an empirical social science study and requires models to reason about policy interventions and identification assumptions without access to predefined causal graphs or structural equations. InterveneBench comprises 744 peer-reviewed studies across diverse policy domains. Experimental results show that state-of-the-art LLMs struggle under this setting. To address this limitation, we further propose a multi-agent framework, STRIDES. It achieves significant performance improvements over state-of-the-art reasoning models. Our code and data are available at https://github.com/Sii-yuning/STRIDES.

cs.CY↗

arXiv2026

Rethinking Visual Token Reduction in LVLMs Under Cross-Modal Misalignment

Large Vision-Language Models (LVLMs) encode visual inputs as dense sequences of patch-level tokens to capture fine-grained semantics. These visual tokens often outnumber their textual counterparts by a large margin, leading to substantial computational overhead and limiting the scalability of LVLMs in practice. Previous efforts have explored visual token reduction either prior to or within the large language models (LLMs). However, most in-LLM reduction approaches rely on text-conditioned interactions, implicitly assuming that textual tokens can reliably capture the importance of visual tokens. In this work, we revisit this assumption and reveal causal, semantic, and spatial forms of cross-modal misalignment. These misalignments undermine the effectiveness of text-guided visual token reduction. To address this, we introduce VisionDrop, a training-free, visual-only pruning framework that selects informative visual tokens based on intra-modal (visual-to-visual) attention, without relying on textual signals. To further suppress redundancy throughout the model hierarchy, we treat the visual encoder and the LLM as a unified system and design a progressive pruning pipeline. Our method performs dominant token selection and lightweight contextual merging at multiple stages, enabling fine-grained visual information to be retained even under aggressive token budgets. Extensive experiments across diverse benchmarks show that VisionDrop achieves consistent improvements over existing approaches, despite requiring no additional training or complex modifications. Notably, when integrated with LLaVA-NeXT-7B, VisionDrop achieves a 2.7x reduction in inference latency and 6x in FLOPs, while retaining 95.71% of the original performance.

cs.CV↗

arXiv2026

PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Data

Segmenting 3D objects into parts is a long-standing challenge in computer vision. To overcome taxonomy constraints and generalize to unseen 3D objects, recent works turn to open-world part segmentation. These approaches typically transfer supervision from 2D foundation models, such as SAM, by lifting multi-view masks into 3D. However, this indirect paradigm fails to capture intrinsic geometry, leading to surface-only understanding, uncontrolled decomposition, and limited generalization. We present PartSAM, the first promptable part segmentation model trained natively on large-scale 3D data. Following the design philosophy of SAM, PartSAM employs an encoder-decoder architecture in which a triplane-based dual-branch encoder produces spatially structured tokens for scalable part-aware representation learning. To enable large-scale supervision, we further introduce a model-in-the-loop annotation pipeline that curates over five million 3D shape-part pairs from online assets, providing diverse and fine-grained labels. This combination of scalable architecture and diverse 3D data yields emergent open-world capabilities: with a single prompt, PartSAM achieves highly accurate part identification, and in a Segment-Every-Part mode, it automatically decomposes shapes into both surface and internal structures. Extensive experiments show that PartSAM outperforms state-of-the-art methods by large margins across multiple benchmarks, marking a decisive step toward foundation models for 3D part understanding.

cs.CV↗

arXiv2026

EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines

While LLM-based agents have shown promise for deep research, most existing approaches rely on fixed workflows that struggle to adapt to real-world, open-ended queries. Recent work therefore explores self-evolution by allowing agents to rewrite their own code or prompts to improve problem-solving ability, but unconstrained optimization often triggers instability, hallucinations, and instruction drift. We propose EvoFSM, a structured self-evolving framework that achieves both adaptability and control by evolving an explicit Finite State Machine (FSM) instead of relying on free-form rewriting. EvoFSM decouples the optimization space into macroscopic Flow (state-transition logic) and microscopic Skill (state-specific behaviors), enabling targeted improvements under clear behavioral boundaries. Guided by a critic mechanism, EvoFSM refines the FSM through a small set of constrained operations, and further incorporates a self-evolving memory that distills successful trajectories as reusable priors and failure patterns as constraints for future queries. Extensive evaluations on five multi-hop QA benchmarks demonstrate the effectiveness of EvoFSM. In particular, EvoFSM reaches 58.0% accuracy on the DeepSearch benchmark. Additional results on interactive decision-making tasks further validate its generalization.

cs.AI↗