arXiv subjects

Fei Hu

Publications and source records attributed to Fei Hu.

At least 19 recordsLinked to original sources

arXiv2026

Not All Agreement Counts as Corroboration: Provenance-Conserving Multi-View Fusion for Typed Action Admission in Human-Robot Collaboration

For embodied systems, predictive agreement alone does not determine whether evidence warrants action; evidential origin matters. Repeated inference over one observation can multiply agreement without adding evidence, while source-local values do not reveal whether outputs have separately countable origins. PACT treats evidence countability as a relational variable for provenance-conserving fusion and typed action admission. A supplied provenance partition defines countable units. PACT retains coordinatewise support shared within each unit, accumulates only across units, and maps unmet release conditions to hold, confirm, or fallback. Under the stated assumptions, source-local values cannot identify countability; the coordinatewise meet is the greatest budget satisfying singleton fidelity and insertion non-amplification, with coarsening monotonicity and fixed-partition stability. Across 31,200 evaluations in 48 scene clusters, PACT attains a common-support normalized risk-coverage area (ncsAURC) of 0.0861. Excluding the constructed adversarial-consensus arm, provenance-partition aggregation reduces ncsAURC by 0.0557 relative to singleton aggregation, while the corroboration contrast vanishes. On complete-source records, native scores favor PACT, but a common posterior-peak score narrows its difference from nested Dirichlet and favors product fusion. Reassigning provenance over unchanged predictions moves evidence budgets as predicted. In offline human-robot collaboration, eightfold within-camera duplication leaves 720 typed responses per checkpoint unchanged; camera-grouped PACT admits 47 of 57 Qwen3-VL-32B reference-consistent candidates with no observed reference-inconsistent admission in 60 episodes. PACT separates computational from evidential multiplicity: agreement constitutes corroboration only when provenance permits separate accumulation.

cs.RO↗

arXiv2026

Preference Flow Matching with Spectral Factorization for Micro-video Recommendation

Micro-video recommendation aims to infer user preferences from historical interactions and multimodal video content, thereby identifying the next video of interest. However, prevailing methods compress frame sequences into a single holistic representation, entangling the stable visual semantics and the evolving dynamics that jointly shape user preferences. Meanwhile, diffusion- and flow matching-based recommenders condition their generation process solely on coarse behavioral context, leaving its internal temporal structure outside preference formation. We therefore propose PrismRec, a Preference Flow Matching framework with Spectral Factorization for Micro-video Recommendation. Analogous to a prism that disperses white light into its constituent spectrum, PrismRec devises Spectral Semantic Factorization (SSF) to derive complementary static semantic and dynamic factors from frame-level representations via a prior-guided learnable frequency mask in the temporal frequency domain. Then, it proposes Context-Calibrated Preference Matching (CPM) to weigh them with each user's specific sensitivity and inject the calibrated context as a structured condition to steer the matching trajectory toward the target representation, making video content as an intrinsic driver of preference formation rather than auxiliary side information. Experiments on four datasets from two platforms show that PrismRec surpasses the SOTA baseline by up to 22.65%, with the lowest inference cost and peak memory among the compared methods.

cs.IR↗

arXiv2026

DiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion

Single-image 3D human reconstruction often suffers from over-smoothed textures and geometric inconsistencies. While diffusion models improve generative quality, their reliance on multi-view synthesis prior to 3D reconstruction is computationally expensive and prone to view inconsistency. We propose DiGS-Avatar, which reformulates this task as an efficient, diffusion-based UV-latent completion task, ensuring 3D consistency by design. To capture accurate spatial structure, we introduce a teacher-student framework where a multi-view teacher provides geometrically aligned pseudo-ground-truth latents to supervise a single-view diffusion student. Treating this inferred latent as a robust structural skeleton, our method injects high-level semantic features to accurately recover fine textural details without disrupting spatial integrity. The refined representation is then decoded into 3D Gaussian primitives. Extensive experiments demonstrate that DiGS-Avatar achieves state-of-the-art or highly competitive visual fidelity and zero-shot generalization, while reconstructing a fully animatable 3D avatar in just 0.71 seconds. Code is available at https://github.com/KLMAV-CUC/DiGS-Avatar.

cs.CV↗

arXiv2026

A lower bound for polynomial volume growth of automorphisms of zero entropy

Let $X$ be a normal projective variety of dimension $d$, and let $f$ be a zero-entropy automorphism of $X$. Denote by $k$ the first-degree growth rate of $f$, so that $\deg_1(f^n) \asymp n^{k}$. We prove the sharp lower bound for the polynomial volume growth $\mathrm{plov}(f)$ of $f$: \[ \mathrm{plov}(f) \ge d+\frac{k(k+2)}{4}, \] equivalently giving a sharp lower bound on the Gelfand--Kirillov dimension of the associated twisted homogeneous coordinate ring. This improves previous lower bounds of Keeler and of Lin--Oguiso--Zhang. In the proof, we introduce the notion of dynamical intersection polynomials and give a new characterization of $\mathrm{plov}(f)$ in terms of non-vanishing of intersection numbers. We also establish a gap principle for polynomial volume growth: for every fixed dimension $d\ge 4$, either $\mathrm{plov}(f)=d^2$, or $\mathrm{plov}(f)\le d(d-2) + 2\lfloor d/4 \rfloor$. This reveals a new rigidity phenomenon for zero-entropy automorphisms. As an application, in dimension $4$ we determine all possible values of $\mathrm{plov}$, thereby extending the results of Artin--Van den Bergh for surfaces and Lin--Oguiso--Zhang for threefolds.

math.AG↗

arXiv2026

A Conditional Denoising Diffusion Probabilistic Model for RFI Mitigation in Synthetic Aperture Interferometric Radiometer

In Earth remote sensing, spatial-frequency domain visibility samples are inversely transformed into spatial-domain brightness temperature (BT) images through the signal processing pipeline of synthetic aperture interferometric radiometers (SAIR). However, L-band radio-frequency interference (RFI) contaminates the measured visibilities and severely degrades BT image quality, thereby impairing geophysical parameter retrieval. To address this issue, we propose VFDM, a Visibility-Function Diffusion Model based on Denoising Diffusion Probabilistic Models (DDPM), to mitigate RFI in the spatial-frequency domain while preserving fine-scale structures consistent with natural scene statistics. Furthermore, we construct a comprehensive dataset comprising more than ten thousand pairs of RFI-free natural scene visibility sample sets and their corresponding simulated contaminated counterparts, categorized by varying RFI intensities, numbers, and distributions. Finally, comprehensive experiments on both simulated and real-world data demonstrate the effectiveness and robustness of the proposed VFDM-based approach.

eess.SP↗

arXiv2025

NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents

Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software systems. Most prior evaluations focus on localized code generation, scaffolded completion, or short-term repair tasks, leaving open the question of whether agents can sustain coherent reasoning, planning, and execution over the extended horizons demanded by real-world repository construction. To address this gap, we present NL2Repo Bench, a benchmark explicitly designed to evaluate the long-horizon repository generation ability of coding agents. Given only a single natural-language requirements document and an empty workspace, agents must autonomously design the architecture, manage dependencies, implement multi-module logic, and produce a fully installable Python library. Our experiments across state-of-the-art open- and closed-source models reveal that long-horizon repository generation remains largely unsolved: even the strongest agents achieve below 40% average test pass rates and rarely complete an entire repository correctly. Detailed analysis uncovers fundamental long-horizon failure modes, including premature termination, loss of global coherence, fragile cross-file dependencies, and inadequate planning over hundreds of interaction steps. NL2Repo Bench establishes a rigorous, verifiable testbed for measuring sustained agentic competence and highlights long-horizon reasoning as a central bottleneck for the next generation of autonomous coding agents.

cs.CL↗

arXiv2025

Parity and symmetry of polarized endomorphisms on cohomology

We show that the eigenvalues of any polarized endomorphism acting on the $\ell$-adic \'etale cohomology of a smooth projective variety satisfy certain parity and symmetry properties, as predicted by the standard conjectures. These properties were previously known for Frobenius endomorphisms. Besides the hard Lefschetz theorem, a key new ingredient is a recent Weil's Riemann hypothesis-type result due to J.~Xie. We also prove a "Newton over Hodge" type property for abelian varieties and Grassmannians.

math.AG↗

arXiv2025

Mano Technical Report

Graphical user interfaces (GUIs) are the primary medium for human-computer interaction, yet automating GUI interactions remains challenging due to the complexity of visual elements, dynamic environments, and the need for multi-step reasoning. Existing methods based on vision-language models (VLMs) often suffer from limited resolution, domain mismatch, and insufficient sequential decisionmaking capability. To address these issues, we propose Mano, a robust GUI agent built upon a multi-modal foundation model pre-trained on extensive web and computer system data. Our approach integrates a novel simulated environment for high-fidelity data generation, a three-stage training pipeline (supervised fine-tuning, offline reinforcement learning, and online reinforcement learning), and a verification module for error recovery. Mano demonstrates state-of-the-art performance on multiple GUI benchmarks, including Mind2Web and OSWorld, achieving significant improvements in success rate and operational accuracy. Our work provides new insights into the effective integration of reinforcement learning with VLMs for practical GUI agent deployment, highlighting the importance of domain-specific data, iterative training, and holistic reward design.

cs.MM↗

arXiv2025

FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

Search has emerged as core infrastructure for LLM-based agents and is widely viewed as critical on the path toward more general intelligence. Finance is a particularly demanding proving ground: analysts routinely conduct complex, multi-step searches over time-sensitive, domain-specific data, making it ideal for assessing both search proficiency and knowledge-grounded reasoning. Yet no existing open financial datasets evaluate data searching capability of end-to-end agents, largely because constructing realistic, complicated tasks requires deep financial expertise and time-sensitive data is hard to evaluate. We present FinSearchComp, the first fully open-source agent benchmark for realistic, open-domain financial search and reasoning. FinSearchComp comprises three tasks -- Time-Sensitive Data Fetching, Simple Historical Lookup, and Complex Historical Investigation -- closely reproduce real-world financial analyst workflows. To ensure difficulty and reliability, we engage 70 professional financial experts for annotation and implement a rigorous multi-stage quality-assurance pipeline. The benchmark includes 635 questions spanning global and Greater China markets, and we evaluate 21 models (products) on it. Grok 4 (web) tops the global subset, approaching expert-level accuracy. DouBao (web) leads on the Greater China subset. Experimental analyses show that equipping agents with web search and financial plugins substantially improves results on FinSearchComp, and the country origin of models and tools impact performance significantly.By aligning with realistic analyst tasks and providing end-to-end evaluation, FinSearchComp offers a professional, high-difficulty testbed for complex financial search and reasoning.

cs.LG↗

arXiv2025

Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

Large Language Models (LLMs) achieve strong performance on diverse tasks but often exhibit cognitive inertia, struggling to follow instructions that conflict with the standardized patterns learned during supervised fine-tuning (SFT). To evaluate this limitation, we propose Inverse IFEval, a benchmark that measures models Counter-intuitive Abilitytheir capacity to override training-induced biases and comply with adversarial instructions. Inverse IFEval introduces eight types of such challenges, including Question Correction, Intentional Textual Flaws, Code without Comments, and Counterfactual Answering. Using a human-in-the-loop pipeline, we construct a dataset of 1012 high-quality Chinese and English questions across 23 domains, evaluated under an optimized LLM-as-a-Judge framework. Experiments on existing leading LLMs demonstrate the necessity of our proposed Inverse IFEval benchmark. Our findings emphasize that future alignment efforts should not only pursue fluency and factual correctness but also account for adaptability under unconventional contexts. We hope that Inverse IFEval serves as both a diagnostic tool and a foundation for developing methods that mitigate cognitive inertia, reduce overfitting to narrow patterns, and ultimately enhance the instruction-following reliability of LLMs in diverse and unpredictable real-world scenarios.

cs.CL↗

arXiv2025

LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering

Video Question Answering (VideoQA) requires identifying sparse critical moments in long videos and reasoning about their causal relationships to answer semantically complex questions. While recent advances in multimodal learning have improved alignment and fusion, current approaches remain limited by two prevalent but fundamentally flawed strategies: (1) task-agnostic sampling indiscriminately processes all frames, overwhelming key events with irrelevant content; and (2) heuristic retrieval captures superficial patterns but misses causal-temporal structures needed for complex reasoning. To address these challenges, we introduce LeAdQA, an innovative approach that bridges these gaps through synergizing causal-aware query refinement with fine-grained visual grounding. Our method first leverages LLMs to reformulate question-option pairs, resolving causal ambiguities and sharpening temporal focus. These refined queries subsequently direct a temporal grounding model to precisely retrieve the most salient segments, complemented by an adaptive fusion mechanism dynamically integrating the evidence to maximize relevance. The integrated visual-textual cues are then processed by an MLLM to generate accurate, contextually-grounded answers. Experiments on NExT-QA, IntentQA, and NExT-GQA demonstrate that our method's precise visual grounding substantially enhances the understanding of video-question relationships, achieving state-of-the-art (SOTA) performance on complex reasoning tasks while maintaining computational efficiency.

cs.CV↗

arXiv2025

Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction

Recent advancements in generalizable novel view synthesis have achieved impressive quality through interpolation between nearby views. However, rendering high-resolution images remains computationally intensive due to the need for dense sampling of all rays. Recognizing that natural scenes are typically piecewise smooth and sampling all rays is often redundant, we propose a novel depth-guided bundle sampling strategy to accelerate rendering. By grouping adjacent rays into a bundle and sampling them collectively, a shared representation is generated for decoding all rays within the bundle. To further optimize efficiency, our adaptive sampling strategy dynamically allocates samples based on depth confidence, concentrating more samples in complex regions while reducing them in smoother areas. When applied to ENeRF, our method achieves up to a 1.27 dB PSNR improvement and a 47% increase in FPS on the DTU dataset. Extensive experiments on synthetic and real-world datasets demonstrate state-of-the-art rendering quality and up to 2x faster rendering compared to existing generalizable methods. Code is available at https://github.com/KLMAV-CUC/GDB-NeRF.

cs.CV↗

arXiv2025

GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis

Neural Radiance Fields (NeRF) have transformed novel view synthesis by modeling scene-specific volumetric representations directly from images. While generalizable NeRF models can generate novel views across unknown scenes by learning latent ray representations, their performance heavily depends on a large number of multi-view observations. However, with limited input views, these methods experience significant degradation in rendering quality. To address this limitation, we propose GoLF-NRT: a Global and Local feature Fusion-based Neural Rendering Transformer. GoLF-NRT enhances generalizable neural rendering from few input views by leveraging a 3D transformer with efficient sparse attention to capture global scene context. In parallel, it integrates local geometric features extracted along the epipolar line, enabling high-quality scene reconstruction from as few as 1 to 3 input views. Furthermore, we introduce an adaptive sampling strategy based on attention weights and kernel regression, improving the accuracy of transformer-based neural rendering. Extensive experiments on public datasets show that GoLF-NRT achieves state-of-the-art performance across varying numbers of input views, highlighting the effectiveness and superiority of our approach. Code is available at https://github.com/KLMAV-CUC/GoLF-NRT.

cs.CV↗

arXiv2025

Tate's question, Standard conjecture D, semisimplicity and Dynamical degree comparison conjecture

Let $X$ be a smooth projective variety of dimension $n$ over the algebraic closure of a finite field $\mathbb{F}_p$. Assuming the standard conjecture $D$, we prove a weaker form of the Dynamical Degree Comparison conjecture; equivalence of semisimplicity of Frobenius endomorphism and of any polarized endomorphism (a more general result, in terms of the biggest size of Jordan blocks, holds). We illustrate these results through examples, including varieties dominated by rational maps from Abelian varieties and suitable products of $K3$ surfaces. Using the same idea, we provide a new proof of the main result in a recent paper by the third author, including Tate's question/Serre's conjecture that for a polarized endomorphism $f:X\rightarrow X$, all eigenvalues of the action of $f$ on $H^k(X)$ have the same absolute value.

math.AG↗

arXiv2024

An upper bound for polynomial volume growth of automorphisms of zero entropy

Let $X$ be a normal projective variety of dimension $d$ over an algebraically closed field and $f$ an automorphism of $X$. Suppose that the pullback $f^*|_{\mathsf{N}^1(X)_\mathbf{R}}$ of $f$ on the real N\'eron--Severi space $\mathsf{N}^1(X)_\mathbf{R}$ is unipotent and denote the index of the eigenvalue $1$ by $k+1$. We establish the following upper bound for the polynomial volume growth $\mathrm{plov}(f)$ of $f$: \[ \mathrm{plov}(f) \le (k/2 + 1)d. \] This inequality is optimal in certain cases. Moreover, we prove that $k\le 2(d-1)$, extending a result of Dinh--Lin--Oguiso--Zhang for compact K\"ahler manifolds to arbitrary characteristic. By combining these two inequalities, we obtain the optimal bound \[ \mathrm{plov}(f) \le d^2, \] that affirmatively answers the questions of Cantat--Paris-Romaskevich and Lin--Oguiso--Zhang.

math.AG↗

arXiv2024

Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking

6D Object Pose Estimation is a crucial yet challenging task in computer vision, suffering from a significant lack of large-scale datasets. This scarcity impedes comprehensive evaluation of model performance, limiting research advancements. Furthermore, the restricted number of available instances or categories curtails its applications. To address these issues, this paper introduces Omni6DPose, a substantial dataset characterized by its diversity in object categories, large scale, and variety in object materials. Omni6DPose is divided into three main components: ROPE (Real 6D Object Pose Estimation Dataset), which includes 332K images annotated with over 1.5M annotations across 581 instances in 149 categories; SOPE(Simulated 6D Object Pose Estimation Dataset), consisting of 475K images created in a mixed reality setting with depth simulation, annotated with over 5M annotations across 4162 instances in the same 149 categories; and the manually aligned real scanned objects used in both ROPE and SOPE. Omni6DPose is inherently challenging due to the substantial variations and ambiguities. To address this challenge, we introduce GenPose++, an enhanced version of the SOTA category-level pose estimation framework, incorporating two pivotal improvements: Semantic-aware feature extraction and Clustering-based aggregation. Moreover, we provide a comprehensive benchmarking analysis to evaluate the performance of previous methods on this large-scale dataset in the realms of 6D object pose estimation and pose tracking.

cs.CV↗

arXiv2023

Canonical heights for abelian group actions of maximal dynamical rank

Let $X$ be a smooth projective variety of dimension $n\geq 2$ and $G\cong\mathbf{Z}^{n-1}$ a free abelian group of automorphisms of $X$ over $\overline{\mathbf{Q}}$. Suppose that $G$ is of positive entropy. We construct a canonical height function $\widehat{h}_G$ associated with $G$, corresponding to a nef and big $\mathbf{R}$-divisor, satisfying the Northcott property. By characterizing its null locus, we prove the Kawaguchi--Silverman conjecture for each element of $G$. As another application, we determine the height counting function for non-periodic points.

math.NT↗

arXiv2023

Vision-Based Human Pose Estimation via Deep Learning: A Survey

Human pose estimation (HPE) has attracted a significant amount of attention from the computer vision community in the past decades. Moreover, HPE has been applied to various domains, such as human-computer interaction, sports analysis, and human tracking via images and videos. Recently, deep learning-based approaches have shown state-of-the-art performance in HPE-based applications. Although deep learning-based approaches have achieved remarkable performance in HPE, a comprehensive review of deep learning-based HPE methods remains lacking in the literature. In this article, we provide an up-to-date and in-depth overview of the deep learning approaches in vision-based HPE. We summarize these methods of 2-D and 3-D HPE, and their applications, discuss the challenges and the research trends through bibliometrics, and provide insightful recommendations for future research. This article provides a meaningful overview as introductory material for beginners to deep learning-based HPE, as well as supplementary material for advanced researchers.

cs.CV↗