论文检索

Deep Learning · Everything Else

Hongtao Huang, Chengkai Huang, Junda Wu, Tong Yu, Julian McAuley, Lina Yao

Forecasting multi-step user behavior trajectories requires reasoning over structured preferences across future actions, a challenge overlooked by traditional sequential recommendation. This problem is critical for applications such as personalized commerce and adaptive content delivery, where anticipating a user’s complete action sequence enhances both satisfaction and business outcomes. We identify an essential limitation of existing paradigms: their inability to capture global, listwise dependencies among sequence items. To address this, we formulate User Behavior Trajectory Prediction (UBTP) as a new task setting that explicitly models longterm user preferences. We introduce Listwise Preference Diffusion Optimization (LPDO), a diffusion-based training framework that directly optimizes structured preferences over entire item sequences. LPDO incorporates a Plackett–Luce supervision signal and derives a tight variational lower bound aligned with listwise ranking likelihoods, enabling coherent preference generation across denoising steps and overcoming the independent-token assumption of prior diffusion methods. To rigorously evaluate multi-step prediction quality, we propose the task-specific metric: Sequential Match (SeqMatch), which measures exact trajectory agreement, and adopt Perplexity (PPL), which assesses probabilistic fidelity. Extensive experiments on real-world user behavior benchmarks demonstrate that LPDO consistently outperforms state-of-the-art baselines, establishing a new benchmark for structured preference learning with diffusion models.

Deep Learning · Everything Else

Sungwoo Park

We introduce Neural Hamiltonian Diffusion, a unified framework for learning stochastic Hamiltonian dynamics on differentiable manifolds. While Hamiltonian Neural Networks (HNNs) model conservative systems in flat Euclidean space, they fail to account for geometric structure and intrinsic stochasticity. Conversely, diffusion models on Riemannian manifolds offer geometry-aware stochastic modeling but lack physical inductive biases. Our method parameterizes a Hamiltonian with a neural network and defines its dynamics as a stochastic differential equation on a (pseudo-)Riemannian manifold equipped with a Poisson structure. This enables physically consistent modeling of dynamics on curved, periodic, or causally structured spaces. We demonstrate that the proposed geometric dynamics generalizes existing approaches and applies to systems ranging from molecular dynamics to relativistic n-body problems.

General Machine Learning · Everything Else

Shikuang Deng, Jiayuan Zhang, Yuhang Wu, Ting Chen, Shi Gu

Hebbian learning is a biological principle that intuitively describes how neurons adapt their connections through repeated stimuli. However, when applied to machine learning, it suffers serious issues due to the unconstrained updates of the connections and the lack of accounting for feedback mediation. Such shortcomings limit its effective scaling to complex network architectures and tasks. To this end, here we introduce the Structural Projection Hebbian Representation (SPHeRe), a novel unsupervised learning method that integrates orthogonality and structural information preservation through a local auxiliary nonlinear block. The loss for structural information preservation backpropagates to the input through an auxiliary lightweight projection that conceptually serves as feedback mediation while the orthogonality constraints account for the boundedness of updating magnitude. Extensive experimental results show that SPHeRe achieves SOTA performance among unsupervised synaptic plasticity approaches on standard image classification benchmarks, including CIFAR-10, CIFAR-100, and Tiny-ImageNet. Furthermore, the method exhibits strong effectiveness in continual learning and transfer learning scenarios, and image reconstruction tasks show the robustness and generalizability of the extracted features. This work demonstrates the competitiveness and potential of Hebbian unsupervised learning rules within modern deep learning frameworks, demonstrating the possibility of efficient and biologically inspired learning algorithms without the strong dependence on strict backpropagation. Our code is available at https://github.com/brain-intelligence-lab/SPHeRe.

Reinforcement Learning · Everything Else

Hossein Goli, Michael Gimelfarb, Nathan de Lara, Haruki Nishimura, Masha Itkina, Florian Shkurti

Off-policy evaluation (OPE) estimates the performance of a target policy using offline data collected from a behavior policy, and is crucial in domains such as robotics or healthcare where direct interaction with the environment is costly or unsafe. Existing OPE methods are ineffective for high-dimensional, long-horizon problems, due to exponential blow-ups in variance from importance weighting or compounding errors from learned dynamics models. To address these challenges, we propose STITCH-OPE, a model-based generative framework that leverages denoising diffusion for long-horizon OPE in high-dimensional state and action spaces. Starting with a diffusion model pre-trained on the behavior data, STITCH-OPE generates synthetic trajectories from the target policy by guiding the denoising process using the score function of the target policy. STITCH-OPE proposes two technical innovations that make it advantageous for OPE: (1) prevents over-regularization by subtracting the score of the behavior policy during guidance, and (2) generates long-horizon trajectories by stitching partial trajectories together end-to-end. We provide a theoretical guarantee that under mild assumptions, these modifications result in an exponential reduction in variance versus long-horizon trajectory diffusion. Experiments on the D4RL and OpenAI Gym benchmarks show substantial improvement in mean squared error, correlation, and regret metrics compared to state-of-the-art OPE methods.

Deep Learning · Everything Else

Yuxi Liu, Min Liu, Shuai Jiang, Yi Tang, Yaonan Wang

Existing NAS methods for semantic segmentation typically apply uniform optimization to all candidate networks (paths) within a one-shot supernet. However, the concurrent existence of both promising and suboptimal paths often results in inefficient weight updates and gradient conflicts. This issue is particularly severe in semantic segmentation due to its complex multi-branch architectures and large search space, which further degrade the supernet's ability to accurately evaluate individual paths and identify high-quality candidates. To address this issue, we propose Dynamic Path Selection (DPS), a selective training strategy that leverages multiple performance proxies to guide path optimization. DPS follows a stage-wise paradigm, where each phase emphasizes a different objective: early stages prioritize convergence, the middle stage focuses on expressiveness, and the final stage emphasizes a balanced combination of expressiveness and generalization. At each stage, paths are selected based on these criteria, concentrating optimization efforts on promising paths, thus facilitating targeted and efficient model updates. Additionally, DPS integrates a dynamic stage scheduler and a diversity-driven exploration strategy, which jointly enable adaptive stage transitions and maintain structural diversity among selected paths. Extensive experiments demonstrate that, under the same search space, DPS can discover efficient models with strong generalization and superior performance.

Applications · Everything Else

Yanwei Ren, Haotian Zhang, Fuxiang Wu, Jiayan Qiu, Jiaxing Huang, Baosheng Yu, Liu Liu

Enhancing large language models by simply scaling up datasets has begun to yield diminishing returns, shifting the spotlight to data quality. Monte Carlo Tree Search (MCTS) has emerged as a powerful technique for generating high-quality chain-of-thought data, yet conventional approaches typically retain only the top-scoring trajectory from the search tree, discarding sibling nodes that often contain valuable partial insights, recurrent error patterns, and alternative reasoning strategies. This unconditional rejection of non-optimal reasoning branches may waste vast amounts of informative data in the whole search tree. We propose SIGMA (Sibling Guided Monte Carlo Augmentation), a novel framework that reintegrates these discarded sibling nodes to refine LLM reasoning. SIGMA forges semantic links among sibling nodes along each search path and applies a two-stage refinement: a critique model identifies overlooked strengths and weaknesses across the sibling set, and a revision model conducts text-based backpropagation to refine the top-scoring trajectory in light of this comparative feedback. By recovering and amplifying the underutilized but valuable signals from non-optimal reasoning branches, SIGMA substantially improves reasoning trajectories. On the challenging MATH benchmark, our SIGMA-tuned 7B model achieves 54.92\% accuracy using only 30K samples, outperforming state-of-the-art models trained on 590K samples. This result highlights that our sibling-guided optimization not only significantly reduces data usage but also significantly boosts LLM reasoning.

Computer Vision · Everything Else

Chen Chen, Majid Abdolshah, Violetta Shevchenko, Hongdong Li, Chang Xu, Pulak Purkait

Existing diffusion-based super-resolution approaches often exhibit semantic ambiguities due to inaccuracies and incompleteness in their text conditioning, coupled with the inherent tendency for cross-attention to divert towards irrelevant pixels. These limitations can lead to semantic misalignment and hallucinated details in the generated high-resolution outputs. To address these, we propose a novel, plug-and-play *spatially re-focused super-resolution (SRSR)* framework that consists of two core components: first, we introduce Spatially Re-focused Cross-Attention (SRCA), which refines text conditioning at inference time by applying visually-grounded segmentation masks to guide cross-attention. Second, we introduce a Spatially Targeted Classifier-Free Guidance (STCFG) mechanism that selectively bypasses text influences on ungrounded pixels to prevent hallucinations. Extensive experiments on both synthetic and real-world datasets demonstrate that SRSR consistently outperforms seven state-of-the-art baselines in standard fidelity metrics (PSNR and SSIM) across all datasets, and in perceptual quality measures (LPIPS and DISTS) on two real-world benchmarks, underscoring its effectiveness in achieving both high semantic fidelity and perceptual quality in super-resolution.

Reinforcement Learning · Everything Else

Yonatan Ashlag, Uri Koren, Mirco Mutti, Esther Derman, Pierre-Luc Bacon, Shie Mannor

State entropy regularization has empirically shown better exploration and sample complexity in reinforcement learning (RL). However, its theoretical guarantees have not been studied. In this paper, we show that state entropy regularization improves robustness to structured and spatially correlated perturbations. These types of variation are common in transfer learning but often overlooked by standard robust RL methods, which typically focus on small, uncorrelated changes. We provide a comprehensive characterization of these robustness properties, including formal guarantees under reward and transition uncertainty, as well as settings where the method performs poorly. Much of our analysis contrasts state entropy with the widely used policy entropy regularization, highlighting their different benefits. Finally, from a practical standpoint, we illustrate that compared with policy entropy, the robustness advantages of state entropy are more sensitive to the number of rollouts used for policy evaluation.

Deep Learning · Everything Else

Xin Gao, Jiyao Liu, Guanghao Li, Yueming Lyu, Jianxiong Gao, Weichen Yu, Ningsheng Xu, Liang Wang, Caifeng Shan, Ziwei Liu 等

Recent advancements have explored text-to-image diffusion models for synthesizing out-of-distribution (OOD) samples, substantially enhancing the performance of OOD detection. However, existing approaches typically rely on perturbing text-conditioned embeddings, resulting in semantic instability and insufficient shift diversity, which limit generalization to realistic OOD. To address these challenges, we propose GOOD, a novel and flexible framework that directly guides diffusion sampling trajectories towards OOD regions using off-the-shelf in-distribution (ID) classifiers. GOOD incorporates dual-level guidance: (1) Image-level guidance based on the gradient of log partition to reduce input likelihood, drives samples toward low-density regions in pixel space. (2) Feature-level guidance, derived from k-NN distance in the classifier’s latent space, promotes sampling in feature-sparse regions. Hence, this dual-guidance design enables more controllable and diverse OOD sample generation. Additionally, we introduce a unified OOD score that adaptively combines image and feature discrepancies, enhancing detection robustness. We perform thorough quantitative and qualitative analyses to evaluate the effectiveness of GOOD, demonstrating that training with samples generated by GOOD can notably enhance OOD detection performance.

Computer Vision · Everything Else

xichen xu, Yanshu Wang, Jinbao Wang, XiaoNing Lei, Guoyang Xie, GUANNAN JIANG, Zhichao Lu

Industrial anomaly segmentation relies heavily on pixel-level annotations, yet real-world anomalies are often scarce, diverse, and costly to label. Segmentation-oriented industrial anomaly synthesis (SIAS) has emerged as a promising alternative; however, existing methods struggle to balance sampling efficiency and generation quality. Moreover, most approaches treat all spatial regions uniformly, overlooking the distinct statistical differences between anomaly and background areas. This uniform treatment hinders the synthesis of controllable, structure-specific anomalies tailored for segmentation tasks. In this paper, we propose FAST, a foreground-aware diffusion framework featuring two novel modules: the Anomaly-Informed Accelerated Sampling (AIAS) and the Foreground-Aware Reconstruction Module (FARM). AIAS is a training-free sampling algorithm specifically designed for segmentation-oriented industrial anomaly synthesis, which accelerates the reverse process through coarse-to-fine aggregation and enables the synthesis of state-of-the-art segmentation-oriented anomalies in as few as 10 steps. Meanwhile, FARM adaptively adjusts the anomaly-aware noise within the masked foreground regions at each sampling step, preserving localized anomaly signals throughout the denoising trajectory. Extensive experiments on multiple industrial benchmarks demonstrate that FAST consistently outperforms existing anomaly synthesis methods in downstream segmentation tasks. We release the code in https://github.com/Chhro123/fast-foreground-aware-anomaly-synthesis.

Computer Vision · Everything Else

chuan guo, Inwoo Hwang, Jian Wang, Bing Zhou

Text-to-motion generation has experienced remarkable progress in recent years. However, current approaches remain limited to synthesizing motion from short or general text prompts, primarily due to dataset constraints. This limitation undermines fine-grained controllability and generalization to unseen prompts. In this paper, we introduce SnapMoGen, a new text-motion dataset featuring high-quality motion capture data paired with accurate, \textit{expressive} textual annotations. The dataset comprises 20K motion clips totaling 44 hours, accompanied by 122 detailed textual descriptions averaging 48 words per description (vs. 12 words of HumanML3D). Importantly, these motion clips preserve original temporal continuity as they were in long sequences, facilitating research in long-term motion generation and blending. We also improve upon previous generative masked modeling approaches. Our model, MoMask++, transforms motion into \textbf{multi-scale} token sequences that better exploit the token capacity, and learns to generate all tokens using a single generative masked transformer. MoMask++ achieves state-of-the-art performance on both HumanML3D and OmniMotion benchmarks. Additionally, we demonstrate the ability to process casual user prompts by employing an LLM to reformat inputs to align with the expressivity and narration style of SnapMoGen.

Computer Vision · Everything Else

Ruoyu Feng, Yunpeng Qi, Jinming Liu, Yixin Gao, Xin Li, Xin Jin, Zhibo Chen

Image compression methods are usually optimized isolatedly for human perception or machine analysis tasks. We reveal fundamental commonalities between these objectives: preserving accurate semantic information is paramount, as it directly dictates the integrity of critical information for intelligent tasks and aids human understanding. Concurrently, enhanced perceptual quality not only improves visual appeal but also, by ensuring realistic image distributions, benefits semantic feature extraction for machine tasks. Based on this insight, we propose Diff-ICMH, a generative image compression framework aiming for harmonizing machine and human vision in image compression. It ensures perceptual realism by leveraging generative priors and simultaneously guarantees semantic fidelity through the incorporation of Semantic Consistency loss (SC loss) during training. Additionally, we introduce the Tag Guidance Module (TGM) that leverages highly semantic image-level tags to stimulate the pre-trained diffusion model's generative capabilities, requiring minimal additional bit rates. Consequently, Diff-ICMH supports multiple intelligent tasks through a single codec and bitstream without any task-specific adaptation, while preserving high-quality visual experience for human perception. Extensive experimental results demonstrate Diff-ICMH's superiority and generalizability across diverse tasks, while maintaining visual appeal for human perception.

Applications · Everything Else

Chengye Yu, Tianyu Wang, Zili Shao, Song Jiang

Large Language Models (LLMs) for multi-turn conversations suffer from inefficiency: semantically similar queries across different user sessions trigger redundant computation and duplicate memory-intensive Key-Value (KV) caches. Existing optimizations such as prefix caching overlook semantic similarities, while typical semantic caches either ignore conversational context or are not integrated with low-level KV cache management. We propose SmartCache, a system-algorithm co-design framework that tackles this inefficiency by exploiting semantic query similarity across sessions. SmartCache leverages a Semantic Forest structure to hierarchically index conversational turns, enabling efficient retrieval and reuse of responses only when both the semantic query and conversational context match. To maintain accuracy during topic shifts, it leverages internal LLM attention scores—computed during standard prefill—to dynamically detect context changes with minimal computational overhead. Importantly, this semantic understanding is co-designed alongside the memory system: a novel two-level mapping enables transparent cross-session KV cache sharing for semantically equivalent states, complemented by a semantics-aware eviction policy that significantly improves memory utilization. This holistic approach significantly reduces redundant computations and optimizes GPU memory utilization. The evaluation demonstrates SmartCache's effectiveness across multiple benchmarks. On the CoQA and SQuAD datasets, SmartCache reduces KV cache memory usage by up to $59.1\%$ compared to prefix caching and $56.0\%$ over semantic caching, while cutting Time-to-First-Token (TTFT) by $78.0\%$ and $71.7\%$, respectively. It improves answer quality metrics, achieving $39.9\%$ higher F1 and $39.1\%$ higher ROUGE-L for Qwen-2.5-1.5B on CoQA. The Semantic-aware Tiered Eviction Policy (STEP) outperforms LRU/LFU by $29.9\%$ in reuse distance under skewed workloads.

Data-centric AI · Everything Else

Jiayi Kuang, Haojing Huang, Yinghui Li, Xinnian Liang, Zhikun Xu, Yangning Li, Xiaoyu Tan, Chao Qu, Meishan Zhang, Ying Shen 等

Large Language Models (LLMs) have demonstrated outstanding performance in mathematical reasoning capabilities. However, we argue that current large-scale reasoning models primarily rely on scaling up training datasets with diverse mathematical problems and long thinking chains, which raises questions about whether LLMs genuinely acquire mathematical concepts and reasoning principles or merely remember the training data. In contrast, humans tend to break down complex problems into multiple fundamental atomic capabilities. Inspired by this, we propose a new paradigm for evaluating mathematical atomic capabilities. Our work categorizes atomic abilities into two dimensions: (1) field-specific abilities across four major mathematical fields, algebra, geometry, analysis, and topology, and (2) logical abilities at different levels, including conceptual understanding, forward multi-step reasoning with formal math language, and counterexample-driven backward reasoning. We propose corresponding training and evaluation datasets for each atomic capability unit, and conduct extensive experiments about how different atomic capabilities influence others, to explore the strategies to elicit the required specific atomic capability. Evaluation and experimental results on advanced models show many interesting discoveries and inspirations about the different performances of models on various atomic capabilities and the interactions between atomic capabilities. Our findings highlight the importance of decoupling mathematical intelligence into atomic components, providing new insights into model cognition and guiding the development of training strategies toward a more efficient, transferable, and cognitively grounded paradigm of "atomic thinking".

Theory · Everything Else

Geonho Hwang

In this paper, we investigate the universal approximation property of deep, narrow multilayer perceptrons (MLPs) for $C^1$ functions under the Sobolev norm, specifically the $W^{1, \infty}$ norm. Although the optimal width of deep, narrow MLPs for approximating continuous functions has been extensively studied, significantly less is known about the corresponding optimal width for $C^1$ functions. We demonstrate that \textit{the optimal width} can be determined in a wide range of cases within the $C^1$ setting. Our approach consists of two main steps. First, leveraging control theory, we show that any diffeomorphism can be approximated by deep, narrow MLPs. Second, using the Borsuk-Ulam theorem and various results from differential geometry, we prove that the optimal width for approximating arbitrary $C^1$ functions via diffeomorphisms is $\min(n + m, \max(2n + 1, m))$ in certain cases, including $(n,m) = (8,8)$ and $(16,8)$, where $n$ and $m$ denote the input and output dimensions, respectively. Our results apply to a broad class of activation functions.

Applications · Everything Else

Zhaoqun Li, Beishui Liao, Qiwei Ye

Mathematicians have long employed decomposition techniques to prove inequalities, yet automating this process remains a significant challenge in computational mathematics. We introduce IneqSearch, a hybrid reasoning system that integrates symbolic computation with large language models (LLMs) to address this challenge. IneqSearch reformulates inequality proving as a structured search problem: identifying appropriate combinations of theorems that decompose expressions into non-negative components. The system combines a symbolic solver for deductive reasoning with an LLM-based agent for constructive proof exploration, effectively implementing methodologies observed in formal mathematical practice. A key contribution of IneqSearch is its iterative learning mechanism that systematically incorporates newly proven results into its theorem database, enabling knowledge acquisition during practice that enhances its capabilities without requiring human intervention. In empirical evaluation on 437 Olympiad-level inequalities, IneqSearch successfully proves 342 problems, significantly outperforming existing methods and demonstrating the effectiveness of integrating symbolic and neural approaches for mathematical reasoning.

Reinforcement Learning · Everything Else

Feichen Gan, Lu Youcun, Yingying Zhang, Yukun Liu

Reliable uncertainty quantification is crucial for reinforcement learning (RL) in high-stakes settings. We propose a unified conformal prediction framework for infinite-horizon policy evaluation that constructs distribution-free prediction intervals for returns in both on-policy and off-policy settings. Our method integrates distributional RL with conformal calibration, addressing challenges such as unobserved returns, temporal dependencies, and distributional shifts. We propose a modular pseudo-return construction based on truncated rollouts and a time-aware calibration strategy using experience replay and weighted subsampling. These innovations mitigate model bias and restore approximate exchangeability, enabling uncertainty quantification even under policy shifts. Our theoretical analysis provides coverage guarantees that account for model misspecification and importance weight estimation. Empirical results, including experiments in synthetic and benchmark environments like Mountain Car, show that our method significantly improves coverage and reliability over standard distributional RL baselines.

Deep Learning · Everything Else

Zhiyuan Ning, Jiawei Shao, Ruge Xu, Xinfei Guo, Jun Zhang, Chi Zhang, Xuelong Li

Speculative decoding has become a widely adopted as an effective technique for lossless inference acceleration when deploying large language models (LLMs). While on-the-fly self-speculative methods offer seamless integration and broad utility, they often fall short of the speed gains achieved by methods relying on specialized training. Cascading a hierarchy of draft models promises further acceleration and flexibility, but the high cost of training multiple models has limited its practical application. In this paper, we propose a novel Cascade Adaptive Self-Speculative Decoding (CAS-Spec) method which constructs speculative draft models by leveraging dynamically switchable inference acceleration (DSIA) strategies, including layer sparsity and activation quantization. Furthermore, traditional vertical and horizontal cascade algorithms are inefficient when applied to self-speculative decoding methods. We introduce a Dynamic Tree Cascade (DyTC) algorithm that adaptively routes the multi-level draft models and assigns the draft lengths, based on the heuristics of acceptance rates and latency prediction. Our CAS-Spec method achieves state-of-the-art acceleration compared to existing on-the-fly speculative decoding methods, with an average speedup from $1.1\times$ to $2.3\times$ over autoregressive decoding across various LLMs and datasets. DyTC improves the average speedup by $47$\% and $48$\% over cascade-based baseline and tree-based baseline algorithms, respectively. CAS-Spec can be easily integrated into most existing LLMs and holds promising potential for further acceleration as self-speculative decoding techniques continue to evolve.

Deep Learning · Everything Else

Yidong Wu, Siyuan Chen, Binrui Wu, Fan Li, Jiechao Gao

In large-scale recommendation systems, multimodal (MM) content is increasingly introduced to enhance the generalization of ID features. The rise of Multimodal Large Language Models (MLLMs) enables the construction of unified user and item representations. However, the semantic distribution gap between MM and ID representations leads to \textit{convergence inconsistency} during joint training: the ID branch converges quickly, while the MM branch requires more epochs, thus limiting overall performance. To address this, we propose a two-stage framework including MM representation learning and joint training optimization. First, we fine-tune the MLLM to generate unified user and item representations, and introduce collaborative signals by post-aligning user ID representations to alleviate semantic differences. Then, we propose an Adaptive Gradient Masking (AGM) training strategy to dynamically regulate parameter updates between ID and MLLM branches. AGM estimates the contribution of each representation with mutual information, and applies non-uniform gradient masking at the sub-network level to balance optimization. We provide theoretical analysis of AGM's effectiveness and further introduce an unbiased variant, AGM*, to enhance training stability. Experiments on offline and online A/B tests validate the effectiveness of our approach in mitigating convergence inconsistency and improving performance.

Computer Vision · Everything Else

Qirui Yang, Yinbo Li, Yihao Liu, Peng-Tao Jiang, Fangpu Zhang, cheng qihua, Huanjing Yue, Jingyu Yang

Existing tone mapping methods operate on downsampled inputs and rely on handcrafted pyramids to recover high-frequency details. Existing tone mapping methods operate on downsampled inputs and rely on handcrafted pyramids to recover high-frequency details. These designs typically fail to preserve fine textures and structural fidelity in complex HDR scenes. Furthermore, most methods lack an effective mechanism to jointly model global tone consistency and local contrast enhancement, leading to globally flat or locally inconsistent outputs such as halo artifacts. We present the Differential Pyramid Representation Network (DPRNet), an end-to-end framework for high-fidelity tone mapping. At its core is a learnable differential pyramid that generalizes traditional Laplacian and Difference-of-Gaussian pyramids through content-aware differencing operations across scales. This allows DPRNet to adaptively capture high-frequency variations under diverse luminance and contrast conditions. To enforce perceptual consistency, DPRNet incorporates global tone perception and local tone tuning modules operating on downsampled inputs, enabling efficient yet expressive tone adaptation. Finally, an iterative detail enhancement module progressively restores the full-resolution output in a coarse-to-fine manner, reinforcing structure and sharpness. Experiments show that DPRNet achieves state-of-the-art results, improving PSNR by **2.39 dB** on the 4K HDR+ dataset and **3.01 dB** on the 4K HDRI Haven dataset, while producing perceptually coherent, detail-preserving results. Demo available at [DPRNet](https://xxxxxxdprnet.github.io/DPRNet/).