arXiv subjects

Jian Xu

Publications and source records attributed to Jian Xu.

At least 73 records · Page 4Linked to original sources

arXiv2026

Onsager-Machlup Posterior Transport for Deep Gaussian Processes

Approximate inference over inducing variables is the central computational bottleneck of Deep Gaussian Processes (DGPs). Existing methods either fit an explicit density $q_ϕ(\bU)$ by an ELBO (DSVI, IPVI, DDVI, DBVI) or sample by MCMC (SGHMC). We instead frame DGP inference as \emph{posterior transport}: learn a deterministic sampler that maps a tractable reference measure to posterior-relevant inducing variables, regularised by a path prior derived from the Doob-bridged reference diffusion. Our realisation, \textbf{OM-Path} (formally FBVI-bridge-Path), uses Song's probability-flow ODE applied to DBVI's Doob-bridged forward SDE; the reference drift is closed-form from the bridge marginal coefficients (no score matching) and the path regulariser is the \textbf{Onsager--Machlup action}. At the finite-$ε$ value used at training, the objective is the negative log unnormalised density of a tempered Doob-bridge path posterior, and Theorem 1 identifies it with the same posterior's small-noise MAP path via the Freidlin--Wentzell LDP. Two strict path-space ELBO variants on the same bridge backbone (FFJORD log-det; OM-regularised CNF) are derived as ablations. Under a matched-seed paired Wilcoxon test against DBVI on seven UCI regression benchmarks, OM-Path delivers statistically significant wins on the two largest datasets (\textit{power}: $p\!=\!0.014$, NLL $\mathbf{0.012}$ matching the DSVI baseline of $0.017$; \textit{protein}: $p\!=\!0.002$, RMSE $\mathbf{0.716}$ vs.\ $0.764$, NLL $\mathbf{1.086}$ vs.\ $1.149$), statistical ties on \textit{yacht} / \textit{qsar}, and concedes \textit{boston} / \textit{energy} / \textit{concrete} to DBVI on small-$N$ noisy data. The strict-ELBO variants do not clear DBVI on any UCI metric: in this regime, reducing the variance of the path objective dominates exact-density tracking.

cs.LG↗

arXiv2026

Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding

While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image reasoning presents fundamental challenges including complex inter-relationships between images and scattered critical information across image sets. Inspired by human cognitive processes, we propose a Cognition-Inspired Meta-Action Framework (CINEMA), which decomposes multi-image reasoning into five structured meta-actions: Global, Focus, Hint, Think, and Answer, explicitly modeling the sequential cognitive steps humans naturally employ. For cold-start training, we introduce a Retrieval-Based Tree Sampling strategy that generates high-quality meta-action trajectories to bootstrap the model with reasoning patterns. During reinforcement learning, we adopt a two-stage paradigm: an exploration phase with Diversity-Preserving Strategy to avoid entropy collapse, followed by an annealed exploitation phase with DAPO to gradually strengthen exploitation. To train our model, we construct a dataset of 56k cold-start and 58k reinforcement learning instances spanning multi-image, multi-frame, and single-image tasks. We conduct extensive evaluations on multi-image reasoning benchmarks, video understanding benchmarks, and single-image benchmarks, achieving competitive state-of-the-art performance on several key benchmarks. Our model surpasses GPT-4o on the MUIR and MVMath benchmarks and notably outperforms specialized video reasoning models on video understanding benchmarks, demonstrating the effectiveness and generalizability of our human cognition-inspired reasoning framework.

cs.CV↗

arXiv2026

Intrinsic Flow Matching on Quantum Pure-State Manifolds with Phase-Aligned Transport

Quantum pure-state ensembles live on complex projective space, making flat Euclidean generative modeling geometrically mismatched. We introduce Intrinsic Flow Matching (IFM), a deterministic transport framework on $\mathbb{CP}^{d-1}$ that learns tangent velocity fields using Pancharatnam phase-aligned conditional paths. IFM replaces local score teachers and reverse-time stochastic sampling with manifold probability flow, while horizontal parameterization removes redundant ambient directions. We show that the IFM objective recovers the induced marginal transport field, represents deterministic projective ensemble flows, and yields endpoint and stability guarantees. Empirically, IFM often improves over ambient Euclidean flow matching across higher-qubit, multimodal, spin-coherent, physics-inspired, and amplitude-encoded MNIST image-vector benchmarks, with strongest gains on high-dimensional and coherence-sensitive tasks but not uniformly across every metric.

cs.LG↗

arXiv2026

Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search

Auto-bidding is a critical tool for advertisers to improve advertising performance. Recent progress has demonstrated that AI-Generated Bidding (AIGB), which learns a conditional generative planner from offline data, achieves superior performance compared to typical offline reinforcement learning (RL)-based auto-bidding methods. However, existing AIGB methods still face a performance bottleneck due to their inherent inability to explore beyond the static dataset with feedback. To address this, we propose \textbf{AIGB-Pearl} (\emph{\textbf{P}lanning with \textbf{E}valu\textbf{A}tor via \textbf{RL}}), a novel method that integrates generative planning and policy optimization. The core of AIGB-Pearl lies in constructing a trajectory evaluator to assess the quality of generated scores and designing a provably sound KL-Lipschitz-constrained score-maximization scheme to ensure safe and efficient exploration beyond the offline dataset. A practical algorithm that incorporates the synchronous coupling technique is further developed to ensure the model regularity required by the proposed scheme. Extensive experiments on both simulated and real-world advertising systems demonstrate the state-of-the-art performance of our approach.

cs.LG↗

arXiv2026

Higher-Order Token Interactions via Quantum Attention

Standard dot-product self-attention computes, in a single layer, only pairwise (order-2) interactions between tokens; representing a generic order-$k$ interaction is known to require either super-quadratic resources in one layer or composition across depth. We introduce \textbf{Quantum Higher-Order Attention (QHA)}, a shallow, hardware-realizable quantum attention head that, via data re-uploading and an all-to-all non-Clifford entangler, synthesizes order-$k$ token interactions inside the circuit and exposes them through a local single-qubit read-out. We prove (i) an expressivity separation: any single standard self-attention layer with embedding dimension $m$, $H$ heads and $p$-bit precision satisfying $mHp=o(N/\log\log N)$ cannot represent the order-$k$ correlation family that one QHA head represents with circuit depth $O(\log k)$ ($O(k)$ two-qubit gates); and (ii) a trainability guarantee for its local-design instantiation: with a local read-out and $O(\log n)$ depth the gradient variance is $Ω(1/\mathrm{poly}(n))$ (no barren plateau), which we confirm empirically -- while being explicit that the more expressive all-to-all instantiation we benchmark is trained empirically and shows exponentially decaying gradients. Empirically, at a $6.5\times$ smaller parameter budget, QHA generalizes hidden-subset parity of every order $k\le6$ from disjoint inputs, whereas the larger classical attention head collapses past order~2; consistent with theory, the size of the advantage tracks the target's Fourier degree - largest for parity and shrinking when low-order structure is present. As an application, QHA serves as a compact high-order interaction detector across three domains - genetic epistasis, learning-parity-with-noise, and graph triangle detection - reaching the noise ceiling at the smallest parameter budget where field-standard linear methods fail.

quant-ph↗

arXiv2026

Effective Dimension Governs Generalization in Quantum Kernel Vision Models

Recent quantum vision models-quantum vision transformers and quantum convolutional networks-report two striking but unexplained empirical phenomena: (i) ansatze with more, or more uniformly distributed, entanglement generalize better, and (ii) injecting quantum noise can improve test accuracy rather than degrade it. These observations are currently treated as curiosities, discovered by grid search and explained, if at all, by hand. We show that both are manifestations of a single, measurable quantity: the \emph{effective dimension} $d_{\rm eff}$ of the (noise-shaped) quantum feature kernel. Working primarily with quantum-kernel vision models-a quantum feature map read out by a kernel classifier-we give a spectral account in which entanglement structure and quantum noise are two knobs that move $d_{\rm eff}$; in an overfitting regime, contracting $d_{\rm eff}$ acts as ridge-like regularization. We analyze the mechanism: an \emph{exact} decomposition of the depolarized kernel $K_p=(1-p)^2K+\tfrac{p(2-p)}{D}\mathbf{1}\mathbf{1}^\top$ with $d_{\rm eff}(K_p)\to1$, a contraction result (and its boundary) for amplitude damping, a kernel-machine capacity bound, and a capacity/alignment risk decomposition; the monotone contraction operative in our entangled experiments is verified empirically, not proven in general. Along the one-parameter depolarizing family the collapse is instead exact by construction; we use it only to confirm the kernel decomposition to machine precision and at up to $12$ qubits, not as evidence for $d_{\rm eff}$. Amplitude damping contracts $d_{\rm eff}$ and lifts test accuracy by up to $+13\%$ along an inverted-U sweet spot; the effect's sign flips between the over- and under-fitting regimes; noise injection matches an explicit spectral-filtering frontier. Our results organize two reported anecdotes into a single measurable principle for designing quantum-vision models.

cs.LG↗

arXiv2026

E-VAds: An E-commerce Short Videos Understanding Benchmark for MLLMs

E-commerce short videos represent a high-revenue segment of the online video industry characterized by a goal-driven format and dense multi-modal signals. Current models often struggle with these videos because existing benchmarks focus primarily on general-purpose tasks and neglect the reasoning of commercial intent. In this work, we first propose a multi-modal information density assessment framework to quantify the complexity of this domain. Our evaluation reveals that e-commerce content exhibits substantially higher density across visual, audio, and textual modalities compared to mainstream datasets, establishing a more challenging frontier for video understanding. To address this gap, we introduce E-commerce Video Ads Benchmark, which is the first benchmark specifically designed for e-commerce short video understanding. We curated 3,961 high-quality videos from Taobao covering a wide range of product categories and used a multi-agent system to generate 19,785 open-ended Q&A pairs, which consist of five distinct tasks. Finally, we develop E-VAds-R1, an RL-based reasoning model featuring a multi-grained reward design called MG-GRPO. This strategy provides smooth guidance for early exploration while creating a non-linear incentive for expert-level precision. Experimental results demonstrate that E-VAds-R1 achieves a 109.2% performance gain in commercial intent reasoning with only a few hundred training samples. Data is available at https://github.com/TaobaoTmall-AlgorithmProducts/E-VAds_Benchmark.

cs.CV↗

arXiv2026

Implicit Variational Rejection Sampling

Variational Inference (VI) is a fundamental inference technique in Bayesian machine learning for approximating complex posterior distributions. Traditional VI often relies on the mean-field factorization, which can inadequately capture true posterior complexity. Recent advancements have leveraged neural networks to model implicit distributions, offering increased flexibility. However, the practical constraints of neural network architectures still produces inaccuracies. In this paper, we propose a method called Implicit Variational Rejection Sampling (IVRS), which integrates implicit distributions with rejection sampling to improve the posterior approximation. Our method uses neural networks to construct implicit proposal distributions, and rejection sampling with a discriminator network that estimates the density ratio between the implicit proposal and the true posterior for refining the approximation. Towards this end, we introduce the Implicit Resampling Evidence Lower Bound (IR-ELBO) as a metric to characterize the resampled distribution's quality and derive a tighter variational lower bound. Experimental results demonstrate that our method outperforms traditional variational inference techniques.

cs.LG↗

arXiv2026

CatalyticMLLM: A Graph-Text Multimodal Large Language Model for Catalytic Materials

Property prediction and inverse structural design of catalytic materials are typically modeled as two independent tasks: the former predicts target properties from given structures, whereas the latter generates candidate structures according to desired properties. Although the decoupled paradigm facilitates the implementation of a ``generation--evaluation--screening'' workflow, the inconsistency between the generative model and the property prediction model in terms of representation spaces and training objectives can readily introduce data distribution shifts and evaluator bias, thereby limiting the stability of closed-loop optimization. In this work, we propose CatalyticMLLM, a unified graph--text multimodal large language model for catalytic materials, which integrates property prediction and \textbf{inverse design} within the same model and shared representation space. Under this unified framework, CatalyticMLLM can not only perform reliable property prediction by leveraging three-dimensional structures and textual information, but also generate and screen physically feasible CIF candidates conditioned on target properties, thereby forming a closed-loop optimization workflow of ``inverse design--prediction--screening--redesign.'' Experimental results demonstrate that this unified paradigm outperforms decoupled baselines on both catalytic relaxed-energy prediction and inverse design tasks, validating the effectiveness of jointly modeling property prediction and structure generation within a single multimodal model.

cs.AI↗

arXiv2026

VFEM: Visual Feature Empowered Multivariate Time Series Forecasting with Cross-Modal Fusion

Large time series foundation models often adopt channel-independent architectures to handle varying data dimensions, but this design ignores crucial cross-channel dependencies. Meanwhile, existing cross-modal methods predominantly rely on textual modalities, leaving the spatial pattern recognition capabilities of vision models underexplored for time series analysis. To address these limitations, we propose VFEM, a cross-modal forecasting model that leverages pre-trained large vision models (LVMs) to capture complex cross-variable patterns. VFEM transforms multivariate time series into visual representations, enabling LVMs to perceive spatial relationships that are not explicitly modeled by channel-independent models. Through a dual-branch architecture, visual and temporal features are independently extracted and then fused via cross-modal attention, allowing complementary information from both modalities to enhance forecasting. By freezing the LVM and training only 7.45% of the total parameters, VFEM achieves competitive performance on multiple benchmarks, offering a new perspective on multivariate time series forecasting.

cs.LG↗

arXiv2026

RankGLU: Residual Gated Score Formation for Cross-Sectional Stock Prediction

Cross-sectional stock prediction is closer to a ranking problem than to ordinary return-magnitude regression, since portfolio decisions depend on the relative ordering of assets within each trading date. Existing temporal, graph-based, and market-conditioned attention models have improved stock representation learning, yet the final prediction head is often treated as a minor implementation detail. This paper argues that, under information-coefficient-oriented evaluation, score formation is a critical bottleneck: an over-flexible head can fit unstable return magnitude, whereas an overly linear head may underuse cross-feature interactions. We therefore develop RankGLU, a residual bottleneck gated linear unit for cross-sectional stock ranking. RankGLU keeps a direct linear scoring path and adds a bounded multiplicative branch, thereby preserving a stable ordering route while allowing controlled nonlinear interactions. The method is evaluated on CSI300 and CSI800 under a unified protocol with cross-sectional score normalization and an IC-augmented objective. Multi-seed experiments show that, on CSI300, RankGLU achieves the strongest mean IC among the internally controlled variants, improving from 0.0654+/-0.0052 for the original backbone and 0.0697+/-0.0030 for the ranking-aware backbone to 0.0727+/-0.0037, a gain that is consistent across all five seeds. Its best-seed result also exceeds the corresponding baselines. Ablation results further indicate that removing the GLU prediction head causes the clearest degradation among the tested component changes. Additional relation-path calibrations can produce high single-seed peaks, but their multi-seed behavior is less stable. The evidence suggests that ranking-aware stock models benefit most reliably from bounded residual score formation rather than from indiscriminate architectural expansion.

cs.CE↗

arXiv2026

The Right Measure for Physics-Constrained Generation: A Co-Area Correction for Posterior-Consistent PDE Inverse Problems

Generative models -- diffusion and flow matching -- are increasingly used to solve partial differential equation (PDE) inverse problems, enforcing the governing physics as a \emph{hard constraint} (via projection or guidance) and reporting the resulting samples as a Bayesian posterior with calibrated uncertainty. We show that this widely adopted recipe samples the wrong distribution. Conditioning a generative prior on a hard PDE constraint is conditioning on a measure-zero manifold -- an operation that is intrinsically ambiguous (the Borel--Kolmogorov paradox) and whose physically correct resolution, the small-residual-noise limit, carries a co-area (Fixman) Jacobian factor $[det(JJ^{\top})]^{-1/2}$ that projection- and guidance-based methods silently omit. We make the bias precise, show that it grows with the heterogeneity of the constraint sensitivity, and validate it on controlled problems against an \emph{i.i.d.} ground-truth arbiter. The omitted factor is not a second-order detail: removing it inflates the posterior error to $20\times$ the sampling-noise floor; minimal-displacement projection (as in PCFM) is biased at $9\times$ the floor; and a naive scalar reweighting does not fix it. We introduce \textbf{CoCoS}, a measure-aware constrained sampler that targets the correct co-area posterior, and show that it matches the gold-standard posterior to within sampling noise. Our results imply that ``satisfying the physics'' is not the same as ``sampling the posterior,'' and give a principled correction for uncertainty-aware scientific inference.

cs.LG↗

arXiv2026

HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling

Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding tasks. However, their performance on high-resolution images remains suboptimal. While existing approaches often attribute this limitation to perceptual constraints and argue that MLLMs struggle to recognize small objects, leading them to use "zoom in" strategies for better detail, our analysis reveals a different cause: the main issue is not object size, but rather caused by complex background interference. We systematically analyze this "zoom in" operation through a series of decoupling experiments and propose the Hierarchical Decoupling Framework (HiDe), a training-free framework that uses Token-wise Attention Decoupling (TAD) to decouple the question tokens and identify the key information tokens, then leverages their attention weights to achieve precise alignment with the target visual regions. Subsequently, it employs Layout-Preserving Decoupling (LPD) to decouple these regions from the background and reconstructs a compact representation that preserves essential spatial layouts while eliminating background interference. HiDe sets a new SOTA on V*Bench, HRBench4K, and HRBench8K, boosting Qwen2.5-VL 7B and InternVL3 8B to SOTA (92.1% and 91.6% on V*Bench), even surpassing RL methods. After optimization, HiDe uses 75% less memory than the previous training-free approach. Code is provided in https://tennine2077.github.io/HiDe.github.io/.

cs.CV↗

arXiv2026

Spectral Anatomy of Quantum Gaussian Process Kernels

Two recent results have reshaped quantum Gaussian processes (QGPs). On the one hand, \citet{lowe2025assessing} rule out the exponential speedups claimed by HHL-based QGP regression in the typical, well-conditioned regime; on the other, an independent line of work shows that highly expressive quantum kernels suffer posterior pathologies that break Bayesian optimization. We show that these seemingly unrelated phenomena are governed by the same quantity: the normalized spectral entropy $S(K)/\log n$ of the kernel Gram matrix. We prove a Cauchy--Schwarz tail bound on Nyström approximation error, a finite-sample variance-contraction identity in terms of Bach's degrees of freedom $d_σ(K)$, and a characterization of the \emph{target-dependent} optimal entropy via the intrinsic dimension of the target in the kernel eigenbasis. Empirically, the diagnostic is kernel-agnostic: hardware-efficient, matchgate, IQP \emph{and} RBF/Matérn/RFF/deep-kernel families all collapse onto identical $S/\log n$ curves on dequantization, ECE, and variance-contraction panels. The NLL sweet spot lives at high entropy for smooth targets and at low entropy for band-limited quantum-data targets. The diagnostic transfers from simulator to IBM Heron hardware with median absolute error $3.2\%$ and mean $5.2\%$ in $S/\log n$ across $24$ configurations at $n_q = 4$, with matchgate and IQP within $5\%$ mean and a single HE configuration returning a $30\%$ outlier that drops to $0.5\%$ on rerun (attributed to calibration drift); the same diagnostic transfers to a second Heron backend (mean error $2.7\%$) and to a $n_q = 6$ scale-up on the original backend (mean error $1.7\%$). No error mitigation is applied throughout.

cs.LG↗

arXiv2026

GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks

Generative recommendations (GR), which usually include item tokenizers and generative Large Language Models (LLMs), have demonstrated remarkable success across a wide range of scenarios. The majority of existing research efforts primarily concentrate on developing powerful item tokenizers or advancing LLM decoding strategies to attain superior performance. However, the critical fine-tuning step in GR frameworks, which is essential for adapting LLMs to recommendation data, remains largely unexplored. Current approaches predominantly rely on either the next-token prediction loss of supervised fine-tuning (SFT) or recommendationspecific direct preference optimization (DPO) strategies. Both methods ignore the exploration of possible positive unobserved samples, which is commonly referred to as the exposure bias problem. To mitigate this problem, this paper treats the GR as a multi-step generation task and constructs a GFlowNets-based fine-tuning framework (GFlowGR). The proposed framework integrates collaborative knowledge from traditional recommender systems to create an adaptive trajectory sampler and a comprehensive reward model. Leveraging the diverse generation property of GFlowNets, along with sampling and heuristic weighting techniques, GFlowGR emerges as a promising approach to mitigate the exposure bias problem. Extensive empirical results on two real-world datasets and with two different GR backbones highlight the effectiveness and robustness of GFlowGR.

cs.IR↗

arXiv2026

From Scaling to Structured Expressivity: Rethinking Transformers for CTR Prediction

Despite massive investments in scale, deep models for click-through rate (CTR) prediction often exhibit rapidly diminishing returns -- a stark contrast to the {predictable scaling laws} seen in large language models (LLMs). We identify the root cause as a {fundamental} \textit{structural misalignment}: {standard} Transformers assume sequential compositionality, whereas CTR data demand combinatorial reasoning over {heterogeneous} fields. To restore alignment, we introduce the \textbf{Field-Aware Transformer (FAT)}. {By reconstructing the standard Transformer block with field-centric parameters, FAT achieves \textit{structured expressivity}, {fundamentally shifting the model complexity dependence from the total vocabulary size $n$ with the number of fields $F$ ($n \gg F$).}} Crucially, to decouple model capacity from field cardinality, FAT employs a {Basis-Composed Hypernetwork} to synthesize field-specific parameters from shared bases, further reducing parameter complexity. {Theoretically, we ground this scaling behavior through a formal scaling law based on Rademacher complexity. Empirically, FAT outperforms exisiting state-of-the-art methods with up to \textbf{+4.38\%} AUC improvement, and delivers \textbf{+2.33\%} CTR and \textbf{+0.66\%} RPM in live production.} Our work establishes that scalable recommendation arises not from size alone, but from \textit{structured expressivity} -- architectural coherence with data semantics.

cs.IR↗

arXiv2026

Frequency-Guided Deformable Networks for Continuous Phase Alignment

The core of time series analysis lies in effectively modeling the physical laws within complex signals. Existing Transformer and Convolution Neural Network (CNN) architectures are often constrained by insufficient temporal inductive bias, restricted frequency extraction capabilities, or weak local phase alignment. To this end, this paper proposes Adaptive Network Based on Cascaded Harmonic Offset Routing (ANCHOR), an Adaptive Network based on Cascaded Harmonic Offset Routing. The model utilizes the Real Fast Fourier Transform (RFFT) to extract explicit dominant periods, injecting them as physical anchors into the dilation operators of multi-branch deformable convolutions. This guides the adaptive optimization of sampling locations in the time domain, achieving synergistic modeling of macroscopic periodic priors and microscopic geometric deformations. Furthermore, to address the quantization errors and picket-fence effects introduced by the discrete RFFT, this paper imports a continuously differentiable 1D Gaussian Radial Basis Function interpolation operator to replace traditional linear interpolation. This maintains the differentiability of the interpolation process and enhances the accuracy of sub-pixel phase compensation. Additionally, ANCHOR introduces an asymmetric routing mechanism and orthogonal channel partitioning to dynamically balance the extraction weights between high-energy strong signals and low-energy weak features. Multi-task benchmark experiments demonstrate that ANCHOR achieves the best or solid performance in short-term forecasting, anomaly detection, and time series classification tasks. Code is available at https://github.com/Jwy-EE/Anchor_pub

eess.SP↗

arXiv2026

Creative4U: MLLMs-based Advertising Creative Image Selector with Comparative Reasoning

Creative image in advertising is the heart and soul of e-commerce platform. An eye-catching creative image can enhance the shopping experience for users, boosting income for advertisers and advertising revenue for platforms. With the advent of AIGC technology, advertisers can produce large quantities of creative images at minimal cost. However, they struggle to assess the creative quality to select. Existing methods primarily focus on creative ranking, which fails to address the need for explainable creative selection. In this work, we propose the first paradigm for explainable creative assessment and selection. Powered by multimodal large language models (MLLMs), our approach integrates the assessment and selection of creative images into a natural language generation task. To facilitate this research, we construct CreativePair, the first comparative reasoning-induced creative dataset featuring 8k annotated image pairs, with each sample including a label indicating which image is superior. Additionally, we introduce Creative4U (pronounced Creative for You), a MLLMs-based creative selector that takes into account users' interests. Through Reason-to-Select RFT, which includes supervised fine-tuning with Chain-of-Thought (CoT-SFT) and Group Relative Policy Optimization (GRPO) based reinforcement learning, Creative4U is able to evaluate and select creative images accurately. Both offline and online experiments demonstrate the effectiveness of our approach. Our code and dataset will be made public to advance research and industrial applications.

cs.CV↗