Searcharxiv⌕ Search

arXiv subjects

Zihan Deng

Publications and source records attributed to Zihan Deng.

At least 19 recordsLinked to original sources
arXiv2026

Aes3D: Aesthetic Assessment in 3D Gaussian Splatting

As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build more visually compelling 3D content. However, existing evaluation methods for 3D scenes primarily emphasize reconstruction fidelity and perceptual realism, largely overlooking higher-level aesthetic attributes such as composition, harmony, and visual appeal. This limitation comes from two key challenges: (1) the absence of general 3DGS datasets with aesthetic annotations, and (2) the intrinsic nature of 3DGS as a low-level primitive representation, which makes it difficult to capture high-level aesthetic features. To address these challenges, we propose Aes3D, the first systematic framework for assessing the aesthetics of 3D neural rendering scenes. Aes3D includes Aesthetic3D, the first dataset dedicated to 3D scene aesthetic assessment, built on our proposed annotation strategy for 3D scene aesthetics. In addition, we present Aes3DGSNet, a lightweight model that directly predicts scene-level aesthetic scores from 3DGS representations. Notably, our model operates solely on 3D Gaussian primitives, eliminating the need for rendering multi-view images and thus reducing computational cost and hardware requirements. Through aesthetics-supervised learning on multi-view 3DGS scene representations, Aes3DGSNet effectively captures high-level aesthetic cues and accurately regresses aesthetic scores. Experimental results demonstrate that our approach achieves strong performance while maintaining a lightweight design, establishing a new benchmark for 3D scene aesthetic assessment.

cs.CV↗
arXiv2026

PhoneValue-Bench: A Multimodal Benchmark and Datasets for Consumer Smartphone Recommerce Valuation

As consumer smartphone recommerce scales, buyers must quote binding repurchase prices from seller-uploaded multi-view photos and diagnostic screenshots before devices reach the warehouse. Accurate remote valuation requires fusing noisy cosmetic evidence with identity, battery, lock, and channel risk from screenshots and staff forms, since an error in any modality changes both grade and payout. However, existing multimodal resources mainly target general VLM competence, screen reading, or factory defect detection, and largely overlook staff-aligned trade-in fields, dual appearance/staff ground truth, and executable valuation scorecards. This gap stems from two challenges: (1) the lack of large-scale real trade-in data with audited dual annotations and a compact ranking benchmark kept separate from training labels, and (2) the need to jointly reason over unordered multi-view cosmetics and diagnostic screens under operational deduction rules. To address these challenges, we propose PhoneValue-Bench, a dual-GT evaluation suite with tier-gated scorecards, together with PhoneValue-Corpus, a matched weakly labeled training set of over twenty thousand orders and hundreds of thousands of captioned images. We further present ValueAgent, a staged perception-fusion-valuation reference pipeline aligned with production inspection, plus an executable public scorer and submission schema. Experiments show that ValueAgent reaches a measured 84.1/100 on Bench-Full, with 97.0 appearance fill and 54.1 staff-field fill, establishing a practical dual-GT benchmark for multimodal recommerce valuation.

cs.CV↗
arXiv2026

MetaRefine: Score Refinement with Multi-Level Features for Image Assessment

An image's original dimensions, aspect ratio, and composition provide important cues that can affect its technical and aesthetic quality. Image assessment methods use resizing, cropping, padding, or patch sampling to accommodate different input sizes. However, these operations can alter or obscure original geometric and compositional cues. Existing assessment models also encode rich multi-level visual evidence that can be further extracted and exploited to improve existing models. This motivates us to combine visual evidence with original-image geometry for score refinement without changing the original scoring pipelines. In this paper, we introduce MetaRefine, a metadata-aware score refinement architecture whose lightweight residual heads predict score corrections from geometry, multi-level visual features, and the frozen model's original score. Across 100 configurations on 21 datasets, MetaRefine improves PLCC in 88 configurations and SRCC in 85, with average relative gains of 7.55% and 7.10%, respectively. It reduces MAE in 90 configurations and RMSE in 89, with average relative reductions of 23.27% and 21.93%, respectively. The median parameter overhead is only 1.11%. MetaRefine can further improve state-of-the-art (SOTA) assessment models on multiple benchmarks.

cs.CV↗
arXiv2026

SparseTokenGS: Gaussian-based Sparse-View CBCT Reconstruction via Reusable Token Pool

Sparse-view cone-beam computed tomography is widely used for fast, low-dose volumetric imaging and lesion localization in dentistry and image-guided interventions, but it introduces severe artifacts. Feed-forward Gaussian methods transfer the reconstruction cost to training and decode each coordinate from projection-aligned features and neighboring anchors. However, information from the whole scan is written only when the field is constructed and cannot be retrieved during coordinate decoding, leaving the volume inconsistent within the scan. This is a common limitation of such methods: once the field is fixed, decoding uses only local features and reconstruction quality drops substantially. We propose SparseTokenGS, a Gaussian-based method for sparse-view cone-beam computed tomography reconstruction via a reusable token pool. Anchor Token Fusion and Point-Token Attention query this shared pool at the anchors and at the query coordinates, respectively. The local Gaussian prior is retained, and the volume is reconstructed in one forward pass, without per-scan optimization or a projection-domain loss. On three public chest and dental datasets, SparseTokenGS achieves the highest reconstruction performance among the compared methods. On clinical dental scans, reconstruction from only six projections reaches 29.51 decibels in peak signal-to-noise ratio and a structural similarity of 0.842 against the full-view reference, and off-the-shelf tooth-and-pulp segmentation keeps these structures separable for root-canal localization. Experiments on volcanic rock and chicken show performance after same-object adaptation. A reusable token pool gives feed-forward reconstruction a mechanism that keeps scan-wide context available through decoding and can benefit future rapid clinical lesion localization and analysis. The code is available at: https://github.com/FrankDengAI/SparseTokenGS.

cs.CV↗
arXiv2026

PrefLUT: Reusable and Refinable Personalized Color Editing from Pairwise Preferences

Photographic color editing is inherently personal: the same image can appear too warm, too muted, or already satisfactory to different users. Most lookup table (LUT) and reference-guided methods target a specified appearance rather than model persistent preferences from repeated user choices. To address this gap, we introduce PrefLUT, a reusable and refinable user-preference modeling framework for deployable 3D LUTs, encoding ordered preferred/non-preferred image pairs into a lightweight Reusable User Profile that is reused across queries and refined using additional user preference pairs, without per-user optimization. A Query-Conditioned LUT Predictor combines this profile with each image to predict a LUT latent vector and edit strength. An Identity-Residual LUT Decoder and Edit-Strength Controller then produce an exportable 3D LUT. Experiments on three datasets demonstrate effective personalized editing and general-purpose enhancement. Each quantized profile requires only 260 bytes, and editing takes 1.365 ms/image on an RTX 5090 GPU. We also introduce the Preference-Conditioning Verification Protocol (PCVP), an evaluation protocol to verify whether personalized image edits depend on user preferences and the query image through controlled changes to user profiles, preference orders, pair correspondences, and query images.

cs.CV↗
arXiv2026

COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion

Sequential diagnosis requires ranking diseases from a sparse intake under a public budget of follow-up questions, which is diagnostic triage with missing findings rather than screening of people who have no symptoms. Because laboratory series arrive irregularly and histories remain incomplete, the ranking must be updated as new facts arrive, yet most pipelines are limited by unnamed numeric trends, unverifiable free-form chain of thought, and a negative bias from treating unasked findings as absent. To solve these, we propose COTCAgent, a sparse-intake consultation agent built on Chain-of-Thought Completion (COTC), which couples three modules on one shared ternary evidence log. The Temporal-Statistics Adapter (TSA) turns time series into typed predicates with named statistics, while the COTC module scores diseases with a learnable knowledge-base energy in which unknown findings add zero energy, after which bounded probabilistic completion selects unknown findings under the question budget and writes each answer back as present, absent, or unknown. Edge strengths and an absence scale are trained with listwise ranking under a sparse curriculum, so that the same energy chooses the next finding by a surrogate entropy reduction. Experiments on DDXPlus and MIMIC-IV show that these modules improve ranking under a matched question budget, with information-gain completion above asking nothing or at random and above protocol-matched askers and a local LLM, thereby providing a foundation for future calibrated scoring and prospective preventive consultation.

cs.CL↗
arXiv2026

SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context

Scientific figure quality is bound to the manuscript: a crop can be visually clear and still contradict its caption or the paragraph that cites it. Most image quality assessment and chart-understanding methods target a detached visual surface or a question-answering score, rather than alignment among the figure, its caption, and the citing text. A single end-to-end prompt that sees the image and the text together still mixes what is visible with what the caption and the citing paragraph claim, so fluent wording can raise a visual score and missing text can be treated as low quality. To address this gap, we introduce SciFigQual-Bench, a manuscript-linked benchmark for published CS-conference figures that binds each figure to its caption and to index-resolved citing paragraphs, and scores visual clarity, layout, caption consistency, context consistency, and misleading risk, leaving a dimension unevaluated when its evidence is absent. SFQ-Agent reads the image and the text in separate calls and records modality-specific evidence. A cross-modal judge scores caption and citing-text alignment from those reports, and a deterministic runner keeps the visual scores, sets misleading risk by a fixed rule, and applies the written caps, so each dimension follows the rubric instead of a single end-to-end prompt. Experiments comparing this staged judge with single-pass and OCR-sidecar protocols find the closest point-estimate fit to mean human ratings under staged judging, while the gap between protocols remains small. Caption consistency remains the main gap, and agreement with the rater mean answers a different question from agreement among human raters.

cs.CV↗
arXiv2026

Learnable Randomization as Commitment Against Adaptive Optimizers

A pricing page can walk the posted price up to the last amount a buyer still accepts, a recommender can hold back a better item for a barely acceptable promoted one, and a classifier can shift its boundary once applicants change their features. The system predicts the response and then picks the menu that serves its own objective, so the surplus above the user's cutoff is taken. Playing the single best action publishes that cutoff, while noise on actions the user would never take throws away payoff and teaches the platform that a worse menu is still acceptable. We study unpredictable near-optimal policies (UNOP), which mix uniformly on near-best actions that remain individually rational. The mixture is a commitment about the response. On a finite price grid, when the best sure-demand price strictly out-earns the randomized band, a seller who already knows the curve posts below the band, and the purchase that occurs is deterministic. Knowing that curve is not the same as predicting the next draw. The mixture can be learned and the optimizer can match its best response, while the user's payoff stays higher because the mixture changes which action is targeted. In pricing and in policy-aware recommendation this leaves more surplus than greedy play when the platform optimizes against the curve and more than one action is acceptable. The gain goes away under quality ranking, a singleton near-optimal set, a wrong utility estimate, or a short-horizon explorer. That is also where mixing should be turned off if the other side is trying to cooperate.

cs.GT↗
arXiv2026

Understanding and Correcting Low-Frequency Bias in EEG Foundation Model

Increasing EEG pretraining data scale or model capacity does not consistently improve downstream performance. We identify a persistent low-frequency bias in representations learned by diverse EEG foundation models, which remains across dataset scales, model capacities, and pretraining objectives. Our analysis links this bias to the interaction between EEG's $1/f^α$-like spectral structure and neural networks' tendency to preferentially learn low-frequency components. In masked autoencoders, the $\ell_2$ reconstruction objective further amplifies this imbalance: under comparable relative reconstruction errors, high-power low-frequency components contribute disproportionately to the loss. To address this issue, we introduce FAME, a frequency-balanced masked autoencoding framework that reconstructs time--frequency activity in predefined EEG bands from masked EEG inputs. FAME independently standardizes the reconstruction targets within each band and assigns equal weight to all band-specific losses, thereby balancing supervision across the EEG spectrum. Evaluated on 41 downstream tasks in OmniEEG-Bench, FAME learns more spectrally balanced representations and achieves state-of-the-art performance on 24 of them. These results underscore the importance of balanced spectral supervision for learning transferable EEG representations.

cs.LG↗
arXiv2026

SciFigAlign: Scoring Scientific Figures by Fine-tuned Alignment of Visuals with Manuscript Evidence

Scientific figure assessment in peer review differs fundamentally from general image quality evaluation: a figure must be visually legible, faithfully support the manuscript's claims, and communicate evidence with a clear visual hierarchy. However, if we apply traditional image assessment methods to scientific figure quality assessment, limitations emerge: classic IQA models capture perceptual quality or aesthetics but cannot judge whether a figure serves the paper's scientific argument; CLIP-based methods assess generic image-text correspondence, yet lack understanding of manuscript context; and zero-shot LLM/VLM judges, when repurposed for figure scoring, often yield overly concentrated scores with limited fusion of visual and textual evidence. We introduce an annotated dataset of 3,857 scientific figures from peer-reviewed conference papers, each rated along four peer-review-oriented dimensions: Clarity, Relevance, Informativeness, and Structure. We propose SciFigAlign, a fine-tuned multimodal scorer that grounds figure quality assessment in manuscript evidence. Given a figure crop, caption, citing paragraphs, and light paper context, SciFigAlign fine-tunes CLIP and SciBERT end-to-end with per-modality cross-attention and CubeMLP fusion, jointly optimizing SmoothL1 regression with a within-paper ranking hinge loss. Under paper-level splits, SciFigAlign achieves a macro MAE of 0.3524 and a within-paper pairwise accuracy of 81.64% on the test set with n = 396, a 59% relative error reduction over the best LLM-as-judge baseline with MAE 0.864. Ablations confirm that manuscript-grounded inputs, citing-context denoising, and ranking supervision are all critical, showing that scientific figure assessment requires learned alignment between visual content and manuscript evidence rather than prompting alone, even with state-of-the-art VLMs.

cs.CV↗
arXiv2026

Pretraining Induces a Reusable Spectral Basis for Downstream Task Adaptation

Finetuning pretrained models occurs in a low-dimensional subspace of the full parameter space. Prior work has focused on characterizing this optimization subspace, but largely ignored the complementary question: why do certain directions remain unexplored during finetuning? Are these stable directions irrelevant to downstream tasks, or do they already encode task-relevant structure that requires no further adjustment? Answering this question is central to understanding how pretrained knowledge transfers. Through systematic spectral analysis across vision and language models, we show that the leading singular vectors of pretrained weight matrices remain highly stable under finetuning and are shared across unrelated downstream tasks, revealing that pretraining establishes a reusable spectral coordinate system. Models pretrained on larger datasets exhibit greater spectral stability under distribution shift or task change, directly linking pretraining scale to geometric transferability. Motivated by these findings, we propose a parameter-efficient method that freezes pretrained singular vectors and optimizes only leading spectral coefficients, achieving competitive performance on GLUE with 0.2% trainable parameters. Our results reveal that the stable directions encode transferable structure rather than irrelevant noise: successful pretraining discovers spectral bases that downstream tasks inherit and operate within.

cs.LG↗
arXiv2026

Solve Crude Oil Scheduling Problems by Using Quantum-Classical Hybrid Algorithms

The optimization of front-end crude oil scheduling is a critical determinant of refinery profitability and operational stability. However, the coupling of discrete logistics events (e.g., vessel berthing) with continuous material flows (e.g., pipeline transfers) renders this problem an NP-hard Mixed-Integer Linear Programming (MILP) challenge, often intractable for classical solvers at industrial scales. This study proposes a novel hybrid quantum-classical framework to address these computational bottlenecks. We employ Benders Decomposition to decouple the monolithic model into a discrete Master Problem (MP) and a continuous Subproblem (SP). To exploit the search capabilities of quantum computing, the MP is reformulated as a Quadratic Unconstrained Binary Optimization (QUBO) model and solved via a hybrid quantum solver, while the SP enforces mass balance and quality constraints through iterative optimality and feasibility cuts. Extensive experiments on 15 multi-scale instances demonstrate that the proposed framework significantly outperforms traditional metaheuristics (e.g., Genetic Algorithms, Tabu Search), reducing total operating costs by approximately 73--80% and achieving computational speeds comparable to state-of-the-art commercial solvers (Gurobi). By effectively leveraging global optimality cuts, the method overcomes the tendency of heuristic approaches to trap in local optima, providing a robust and scalable solution for complex refinery logistics.

quant-ph↗
arXiv2026

Local Intrinsic Dimension of Representations Predicts Alignment and Generalization in AI Models and Human Brain

Recent work has found that neural networks with stronger generalization tend to exhibit higher representational alignment with one another across architectures and training paradigms. In this work, we show that models with stronger generalization also align more strongly with human neural activity. Moreover, generalization performance, model--model alignment, and model--brain alignment are all significantly correlated with each other. We further show that these relationships can be explained by a single geometric property of learned representations: the local intrinsic dimension of embeddings. Lower local dimension is consistently associated with stronger model--model alignment, stronger model--brain alignment, and better generalization, whereas global dimension measures fail to capture these effects. Finally, we find that increasing model capacity and training data scale systematically reduces local intrinsic dimension, providing a geometric account of the benefits of scaling. Together, our results identify local intrinsic dimension as a unifying descriptor of representational convergence in artificial and biological systems.

cs.LG↗
arXiv2026

Understanding Generalization from Embedding Dimension and Distributional Convergence

Deep neural networks often generalize well despite heavy over-parameterization, challenging classical parameter-based analyses. We study generalization from a representation-centric perspective and analyze how the geometry of learned embeddings controls predictive performance for a fixed trained model. We show that population risk can be bounded by two factors: (i) the intrinsic dimension of the embedding distribution, which determines the convergence rate of empirical embedding distribution to the population distribution in Wasserstein distance, and (ii) the sensitivity of the downstream mapping from embeddings to predictions, characterized by Lipschitz constants. Together, these yield an embedding-dependent error bound that does not rely on parameter counts or hypothesis class complexity. At the final embedding layer, architectural sensitivity vanishes and the bound is dominated by embedding dimension, explaining its strong empirical correlation with generalization performance. Experiments across architectures and datasets validate the theory and demonstrate the utility of embedding-based diagnostics.

cs.LG↗
arXiv2025

Predictive Modeling: BIM Command Recommendation Based on Large-scale Usage Logs

The adoption of Building Information Modeling (BIM) and model-based design within the Architecture, Engineering, and Construction (AEC) industry has been hindered by the perception that using BIM authoring tools demands more effort than conventional 2D drafting. To enhance design efficiency, this paper proposes a BIM command recommendation framework that predicts the optimal next actions in real-time based on users' historical interactions. We propose a comprehensive filtering and enhancement method for large-scale raw BIM log data and introduce a novel command recommendation model. Our model builds upon the state-of-the-art Transformer backbones originally developed for large language models (LLMs), incorporating a custom feature fusion module, dedicated loss function, and targeted learning strategy. In a case study, the proposed method is applied to over 32 billion rows of real-world log data collected globally from the BIM authoring software Vectorworks. Experimental results demonstrate that our method can learn universal and generalizable modeling patterns from anonymous user interaction sequences across different countries, disciplines, and projects. When generating recommendations for the next command, our approach achieves a Recall@10 of approximately 84%. The code is available at: https://github.com/dcy0577/BIM-Command-Recommendation.git

cs.IR↗
arXiv2025

BIMgent: Towards Autonomous Building Modeling via Computer-use Agents

Existing computer-use agents primarily focus on general-purpose desktop automation tasks, with limited exploration of their application in highly specialized domains. In particular, the 3D building modeling process in the Architecture, Engineering, and Construction (AEC) sector involves open-ended design tasks and complex interaction patterns within Building Information Modeling (BIM) authoring software, which has yet to be thoroughly addressed by current studies. In this paper, we propose BIMgent, an agentic framework powered by multimodal large language models (LLMs), designed to enable autonomous building model authoring via graphical user interface (GUI) operations. BIMgent automates the architectural building modeling process, including multimodal input for conceptual design, planning of software-specific workflows, and efficient execution of the authoring GUI actions. We evaluate BIMgent on real-world building modeling tasks, including both text-based conceptual design generation and reconstruction from existing building design. The design quality achieved by BIMgent was found to be reasonable. Its operations achieved a 32% success rate, whereas all baseline models failed to complete the tasks (0% success rate). Results demonstrate that BIMgent effectively reduces manual workload while preserving design intent, highlighting its potential for practical deployment in real-world architectural modeling scenarios. Project page: https://tumcms.github.io/BIMgent.github.io/

cs.AI↗
arXiv2025

Scale-Invariance Drives Convergence in AI and Brain Representations

Despite variations in architecture and pretraining strategies, recent studies indicate that large-scale AI models often converge toward similar internal representations that also align with neural activity. We propose that scale-invariance, a fundamental structural principle in natural systems, is a key driver of this convergence. In this work, we propose a multi-scale analytical framework to quantify two core aspects of scale-invariance in AI representations: dimensional stability and structural similarity across scales. We further investigate whether these properties can predict alignment performance with functional Magnetic Resonance Imaging (fMRI) responses in the visual cortex. Our analysis reveals that embeddings with more consistent dimension and higher structural similarity across scales align better with fMRI data. Furthermore, we find that the manifold structure of fMRI data is more concentrated, with most features dissipating at smaller scales. Embeddings with similar scale patterns align more closely with fMRI data. We also show that larger pretraining datasets and the inclusion of language modalities enhance the scale-invariance properties of embeddings, further improving neural alignment. Our findings indicate that scale-invariance is a fundamental structural principle that bridges artificial and biological representations, providing a new framework for evaluating the structural quality of human-like AI systems.

q-bio.NC↗
arXiv2024

Towards commands recommender system in BIM authoring tool using transformers

The complexity of BIM software presents significant barriers to the widespread adoption of BIM and model-based design within the Architecture, Engineering, and Construction (AEC) sector. End-users frequently express concerns regarding the additional effort required to create a sufficiently detailed BIM model when compared with conventional 2D drafting. This study explores the potential of sequential recommendation systems to accelerate the BIM modeling process. By treating BIM software commands as recommendable items, we introduce a novel end-to-end approach that predicts the next-best command based on user historical interactions. Our framework extensively preprocesses real-world, large-scale BIM log data, utilizes the transformer architectures from the latest large language models as the backbone network, and ultimately results in a prototype that provides real-time command suggestions within the BIM authoring tool Vectorworks. Subsequent experiments validated that our proposed model outperforms the previous study, demonstrating the immense potential of the recommendation system in enhancing design efficiency.

cs.IR↗