论文检索

Deep Learning · Everything Else

Haosen Wang, Jing Xiao, Mengqiao Li, Xuanze Wang, Mingzheng Zhang, Xiaowang Zhang, Zhiyong Feng

Precise evidence region localization in Document Visual Question Answering (DocVQA) is crucial for improving model interpretability and reliability. However, most existing approaches rely on single-step localization, which struggles to effectively distinguish true evidence from irrelevant content when page semantics are complex or evidence regions are extremely small, leading to ambiguous boundaries and localization errors. To address these challenges, we propose a progressive evidence localization framework based on Wasserstein gradient flows, which reformulates evidence localization as an optimal transport optimization problem over probability distributions. Since continuous-time gradient flows are intractable in practice, we adopt the Jordan--Kinderlehrer--Otto (JKO) scheme for discrete optimization and derive an end-to-end trainable loss function that translates the theoretical framework into a neural network–optimizable objective. This formulation enables precise evidence localization through progressive refinement from coarse-grained to fine-grained regions. Experimental results demonstrate that our method significantly outperforms existing approaches in both evidence localization and answer generation, while providing an interpretable progressive reasoning process.

Deep Learning · Generative Models and Autoencoders

Zihao Cheng, Binrui Wu, Yuesen Liao, Weizhong Zhang

Diffusion probabilistic models (DPMs)’ sampling process is often inefficient, requiring hundreds to thousands of iterative steps to accurately approximate the diffusion trajectory. This inefficiency limits their practical applicability. Although recent advances in sampling efficiency—such as numerical solvers for diffusion ordinary differential equations (ODEs)—have made progress, significant challenges remain: training-free numerical solvers suffer from the suboptimality of manually designed timestep selection rules and the inherent inconsistency between the forward diffusion process (typically involving thousands of steps) and the reverse denoising process (usually limited to tens of steps). Since timestep selection is inherently a discrete problem and cannot be optimized via gradients, we propose an innovative approach—reparameterizing the timestep scheduling through probabilistic masking, thereby enabling gradient-based optimization of sampling timesteps. To circumvent backpropagation, we employ policy gradient methods. Furthermore, to address the inconsistency between forward diffusion (training) and reverse denoising (inference), we extend this framework into a bilevel optimization paradigm: the inner loop performs additional lightweight training on the model at specific timesteps determined by the outer mask to align forward and reverse processes, while the outer loop optimizes the timestep distribution via probabilistic masking and policy gradient based on generation quality. Under mild assumptions, we theoretically analyze the convergence of the proposed algorithm. Extensive experiments across diverse datasets and samplers demonstrate that this framework effectively enhances sampling efficiency and generation quality while maintaining compatibility with various DPM architectures and advanced ODE solvers.

Theory · Reinforcement Learning and Planning

Min Wang, Xin Li, Ye He, Mingzhong Wang, Yonggang Zhang

Meta-Reinforcement Learning (Meta-RL) faces significant challenges in non-parametric settings, where vastly different return scales across diverse tasks cause severe gradient interference. Existing categorical solutions attempt to normalize these scales but often fail due to rigid discretization and quantization errors. To address this, we propose Reflect-then-Correct (RTC), a framework that models meta-values using Sinkhorn divergence. By treating distributions as adaptive floating particles, RTC achieves a geometry-aware alignment of distinct meta-task structures. However, while Sinkhorn updates harmonize gradients, they introduce statistical bias via sampling estimation. RTC overcomes this by ''reflecting'' on the temporal accumulation of Bellman inconsistencies through a recursive error model and ''correcting'' the optimization via adaptive importance weights that prioritize transitions critical for accuracy. We provide theoretical guarantees for this reweighting strategy and demonstrate that RTC outperforms existing baselines on the challenging Meta-World ML-10 and ML-45 benchmarks.

General Machine Learning · Everything Else

Pengyang Huang, Zirui Zhuang, Haifeng Sun, Qi Qi, Jingyu Wang, Jianxin Liao

Deep learning approaches typically require prohibitive amounts of data to approximate strict Exact Cover Problems, while existing neuro-symbolic methods often face training infeasibility and scalability bottlenecks. To bridge this divide, we propose the Hypergraph Optimization Network (HONet), an end-to-end framework integrating a topologically complete Deep Residual Hypergraph Encoder with a differentiable Equality-Constrained Quadratic Programming layer. By adopting a "Fixed Polytope" paradigm guided by the Geometric Consistency Loss, HONet explicitly shapes the objective landscape, forcing the valid discrete solution to align with the unique global energy minimum. Empirical results show that HONet rapidly achieves 100\% accuracy on $9 \times 9$ Sudoku using limited samples, exhibiting superior data efficiency over baselines while maintaining exceptional robustness in highly sparse regimes and additional tasks.

Deep Learning · Generative Models and Autoencoders

Mingkun Lei, Tong Zhao, Liangyu Yuan, Chi Zhang

Step-level caching offers a promising avenue for accelerating diffusion models by exploiting temporal redundancy. However, existing strategies predominantly rely on heuristic, threshold-based metrics to trigger cache updates. This reactive paradigm is inherently myopic as it optimizes only for local feature consistency, and yields unpredictable deployment latency. In this work, we propose BudCache, a budget-constrained optimization framework that inverts this standard: instead of letting error thresholds dictate the cost, we enforce a strict computational budget and globally search for the caching policy that maximizes generation fidelity. To tackle the combinatorial complexity of step selection, we employ a hybrid strategy combining Simulated Annealing with deterministic Hill Climbing. This approach efficiently escapes local optima to locate globally optimized cache masks within minutes, incurring zero inference overhead. Crucially, to address the trajectory drift induced by aggressive caching, we introduce a cache-aware schedule alignment mechanism. By refining the time discretization via a lightweight, data-free distillation, we significantly enhance performance in low-NFE regimes. Extensive experiments on FLUX.1-dev and Wan2.1 demonstrate that BudCache consistently outperforms heuristic baselines, achieving superior perceptual quality under rigid latency constraints.

Zhimeng Guo, Huaisheng Zhu, Siyuan Xu, Hangfan Zhang, Teng Xiao, Minhao Cheng

As LLMs increasingly generate production code, protecting intellectual property demands watermarking techniques that respect code's strict syntactic constraints. In this work, we introduce CodeTracer, an innovative adaptive code watermarking framework underpinned by a reinforcement learning training paradigm. At its core, CodeTracer features a policy-driven approach that utilizes a parameterized model to intelligently bias token choices during next-token prediction. This strategy ensures that embedded watermarks maintain code functionality while exhibiting subtle yet statistically detectable deviations from typical token distributions. To facilitate policy learning, we devise a comprehensive reward system that seamlessly integrates execution feedback with watermark embedding signals, balancing process-level and outcome-level rewards. To enable gradient-based optimization of these discrete watermarking decisions, we employ Gumbel Top-k reparameterization. Extensive comparative evaluations demonstrate that CodeTracer outperforms state-of-the-art baselines across multiple benchmarks in both watermark detectability and code functionality. Our code is available at https://anonymous.4open.science/r/CodeTracer-B8EE.

Theory · Learning Theory

Yuma Ichikawa, Shuhei Kashiwamura, Ayaka Sakata

Quantized neural network training optimizes a discrete, non-differentiable objective. The straight-through estimator (STE) enables backpropagation through surrogate gradients and is widely used. While previous studies have primarily focused on the properties of surrogate gradients and their convergence, the influence of quantization hyperparameters, such as bit width and quantization range, on learning dynamics remains largely unexplored. We theoretically show that in the high-dimensional limit, STE dynamics converge to a deterministic ordinary differential equation. This reveals that STE training exhibits a plateau followed by a sharp drop in generalization error, with plateau length depending on the quantization range. A fixed-point analysis quantifies the asymptotic deviation from the unquantized linear model. We also extend analytical techniques for stochastic gradient descent to nonlinear transformations of weights and inputs.

General Machine Learning · Clustering

Yuemeng Huang, Huibing Wang, Jinjia Peng, Lu Jiang, Qian Liu, Zetian Mi, Jiqing Zhang

Anchor-based multi-view clustering has garnered wide attention for its ability to reduce the computational complexity of large-scale spectral clustering.However, existing methods mostly adopt a unidirectional optimization paradigm confined to sample-anchor bipartite graphs, treating the construction of the consensus graph and discrete clustering assignments as separate sub-problems to be solved independently. This weakens the information exchange between continuous representation and discrete structure, confining the optimization process to iterative updates within local modules.To address these limitations, we propose a Discretely-Refined Multi-view Clustering(DRMC) via Aligned Anchor Learning. Unlike approaches that directly perform fusion in the anchor space, our method starts from the anchor graph, elevates sample-anchor associations to sample-level similarity graph representations, and thereby enhances both within-cluster similarity and between-cluster separation. Furthermore, we design a discrete feedback module that jointly conducts spectral embedding learning and discrete label assignment by orthogonally aligning the continuous embedding matrix with the discrete indicator matrix. The resulting discrete partition is then fed back into the consensus graph construction, continuously refining the graph structure. Experiments on multiple benchmark datasets demonstrate that the proposed method exhibits significant advantages over existing state-of-the-art approaches.

Deep Learning · Large Language Models

Xiangdong Zhang, Debing Zhang, Shaofeng Zhang, Xiaohan Qin, Yu Cheng, Junchi Yan

Standard Next-Token Prediction (NTP) supervises language models solely through discrete labels in the output logit space. We argue that this sparse, one-hot supervision leaves the latent representation space under-constrained, allowing hidden states to drift into degenerate and anisotropic configurations that limit generalization. To address this issue, we propose **Next Implicit Token Prediction (NITP)**, which augments discrete prediction with dense, continuous supervision directly in the representation space. NITP requires the model to predict the implicit semantic content of the next token, using shallow-layer representations from the same model as stable self-supervised targets. Theoretically, we show that NITP regularizes the optimization landscape by eliminating under-constrained degrees of freedom and enforcing a compact, structured representation geometry. Empirically, across dense and MoE models ranging from 0.5B to 9B parameters, NITP consistently **improves downstream performance with negligible computational overhead**. Notably, on the 9B MoE model, NITP achieves a **5.7%** absolute improvement on MMLU-Pro, along with gains of **6.4%** on C3 and **4.3%** on CommonsenseQA, with **~2%** additional training FLOPs and no additional inference cost.

Deep Learning · Sequential Models, Time series

Leon Götz, Marcel Kollovieh, Stephan Günnemann, Leo Schwinn

Existing time series tokenization methods predominantly encode a constant number of samples into individual tokens. This inflexible approach can generate excessive tokens for even simple patterns like extended constant values, resulting in substantial computational overhead. Inspired by the success of byte pair encoding, we propose the first pattern-centric tokenization scheme for time series analysis. Based on a discrete vocabulary of frequent motifs, our method merges samples with underlying patterns into tokens, compressing time series adaptively. Exploiting our finite set of motifs and the continuous properties of time series, we further introduce conditional decoding as a lightweight yet powerful post-hoc optimization method, which requires no gradient computation and adds no computational overhead. On recent time series foundation models, our motif-based tokenization improves forecasting performance by 36% and boosts efficiency by 1990% on average. Conditional decoding further reduces MSE by up to 44%. In an extensive analysis, we demonstrate the adaptiveness of our tokenization to diverse temporal patterns, its generalization to unseen data, and its meaningful token representations capturing distinct time series properties, including statistical moments and trends.

Theory · Learning Theory

Jiaolong Wang, Fode Zhang, Lingrui Wang

Reliable estimation of Amari $\alpha$-divergences underpins variational inference, yet unconstrained neural critics are notoriously prone to instability. We propose a scalable estimator by constraining the critic to a Reproducing Kernel Hilbert Space (RKHS) ball and approximating the kernel via band-limited Random Fourier Features (RFF). This formulation yields a linear-time objective amenable to mini-batch stochastic optimization while avoiding the cubic complexity of Gram-matrix methods. We present a unified analysis based on a four-term error decomposition—comprising RKHS approximation, feature discretization, statistical deviation, and optimization residual. Under a spectral source condition, we derive non-asymptotic bounds establishing that the RKHS approximation bias scales as $\mathcal{O}(R^{-\gamma})$, the RFF discretization error as $\mathcal{O}(R D^{-1/2})$, and the statistical error as $\mathcal{O}(R n^{-1/2})$. We further show that statistical non-degeneracy induces intrinsic local curvature, enabling our proposed Armijo-SGD to achieve local linear convergence. Empirical evaluations demonstrate that the RFF-RKHS estimator outperforms varying-representation baselines in stability, and applying this spectral regularization to GAN critics significantly enhances the capture of high-frequency data components.

Deep Learning · Theory

Sai Niranjan Ramachandran, Suvrit Sra

Decision trees and diffusion models are ostensibly disparate model classes, one discrete and hierarchical, the other continuous and dynamic. This work unifies the two by establishing a crisp mathematical correspondence between hierarchical decision trees and diffusion processes in appropriate limiting regimes. Our unification reveals a shared optimization principle: \emph{Global Trajectory Score Matching (GTSM)}, for which gradient boosting (in an idealized version) is asymptotically optimal. We underscore the conceptual value of our work through two key practical instantiations: \treeflow, which achieves competitive generation quality on tabular data with higher fidelity and a 2× computational speedup, and \dsmtree, a novel distillation method that transfers hierarchical decision logic into neural networks, matching teacher performance within 2\% on many benchmarks.

Applications · Language, Speech and Dialog

Chunsan Hong, Sanghyun Lee, Jong Chul YE

Masked diffusion models (MDMs) are a potential alternative to autoregressive models (ARMs) for language generation, but generation quality depends critically on the generation order. Prior work either hard-codes an ordering (e.g., blockwise left-to-right) or learns an ordering policy for a pretrained MDM, which incurs extra cost and can yield suboptimal solutions due to the two-stage optimization. Motivated by this, we propose order-expressive masked diffusion model (OeMDM) for a broad class of diffusion generative processes with various generation orders, enabling the interpretation of MDM, ARM, and block diffusion in a single framework. Furthermore, building on OeMDM, we introduce learnable-order masked diffusion model (LoMDM), which jointly learns the generation ordering and diffusion backbone through a single objective from scratch, enabling the diffusion model to generate text in context-dependent ordering. Empirically, we confirm that LoMDM outperforms various discrete diffusion models across multiple language modeling benchmarks.

Reinforcement Learning · Deep RL

Yuexin Bian, Jie Feng, Tao Wang, Yijiang Li, Sicun Gao, Yuanyuan Shi

On-policy deep reinforcement learning remains a dominant paradigm for continuous control, yet standard implementations rely on Gaussian actors and relatively shallow MLP policies, often leading to brittle optimization when gradients are noisy and policy updates must be conservative. In this paper, we revisit policy representation as a first-class design choice for on-policy optimization. We study discretized categorical actors that represent each action dimension with a distribution over bins, yielding a policy objective that resembles a cross-entropy loss. Building on architectural advances from supervised learning, we further propose regularized actor networks, while keeping critic design fixed. Our results show that simply replacing the standard actor network with our discretized regularized actor yields consistent gains and achieve the state-of-the-art performance across diverse continuous-control benchmarks.

Applications · Computer Vision

Xiao Cui, Yulei Qin, Mo Zhu, Wengang Zhou, Hongsheng Li, Houqiang Li

Dataset condensation aims to construct compact datasets from real data via synthesis or selection. However, existing approaches are ill-suited for diffusion model training: synthetic data generation often yields low-fidelity samples unsuitable for authentic modeling, while real subset selection typically fails to preserve the distributional geometry required by diffusion likelihood objectives. To address this, we propose to reformulate real subset selection as a geometry-aware distribution alignment problem. By incorporating one-sided partial optimal transport, our method selectively aligns a compact subset with the full data distribution while allowing unmatched mass in low-density regions, ensuring the preserved geometric structure necessary for effective diffusion model training. To further ensure distributional fidelity, we complement geometric alignment with lightweight feature-statistics and semantic consistency regularization. An efficient two-stage discrete optimization strategy is proposed to achieve this alignment objective. Extensive experiments across diffusion variants, subset sizes, image resolutions, and training rounds show that our approach achieves superior fidelity and distributional coverage in diffusion model training. Codes are available at https://anonymous.4open.science/r/ICML2026_4092.

Optimization · Discrete and Combinatorial Optimization

Rongsheng Jia, Yifan Zhang, Jun Zhang, Jian Cheng

Recent decomposition-based approaches have achieved significant success in Multi-Objective Combinatorial Optimization (MOCO). However,existing methods typically rely exclusively on node-centric representations, failing to capture the complementary representations provided by edge features for problem instances, resulting in a persistent optimality gap. To address this , we propose a Preference-Modulated Structural Attention mechanism to enhance problem representation by synergizing node and edge features. It includes: (1) Utilizing preference-modulated edge features as explicit structural biases during attention calculation, enabling model to perceive sub-problem structures conditioned on specific preferences,and (2) an edge feature aggregation strategy that dynamically incorporates node-specific context into edge representations to enhance the perception of preference-aware structures. Experiments on classic MOCOP benchmarks demonstrate the superiority of our approach in terms of both performance and generalization capabilities.

Xinyou Wang, Liang Hong, Jiasheng Ye, Zaixiang Zheng, Shujian Huang, Quanquan Gu

Proteins are shaped by gradual evolution under biophysical and functional constraints. Protein language models learn rich evolutionary constraints from large-scale sequence data, and discrete diffusion–based protein language models (e.g., DPLMs) have emerged as a promising framework for both understanding and generation. However, existing DPLMs typically rely on masking-based absorbing diffusion, which conflicts with a basic biological intuition: proteins evolve through accumulated edits rather than emerging from masked tokens. As a result, these frameworks lack explicit pretraining objectives for substitution and insertion/deletion (indel) operations, which in turn limits both optimization-style post-editing and flexible guided generation. To address these limitations, we present DPLM-Evo, an evolutionary discrete diffusion framework that explicitly predicts substitution, insertion, and deletion operations during denoising. \method decouples a fixed-length latent alignment space from the variable-length observed sequence space, making indel-aware generation tractable and enabling adaptive scaffold growth throughout the process with negligible computational overhead. To further align substitutions with real evolutionary dynamics, we introduce a contextual evolutionary noising kernel that induces biologically informed, context-dependent mutation patterns. Across tasks, \method improves sequence understanding and achieves state-of-the-art performance on ProteinGym in the single-sequence setting, while also enabling variable-length simulated evolution, guided generation, and post-editing or optimization of existing proteins via explicit edit trajectories.

Deep Learning · Foundation Models

Sunil Kothari, Sumukha Sharma Thoppanahalli Chandramouli, Naman Khandelwal, Praveen Kumar Gulipalli, Parth Kulshreshtha, Ashi Jain, Kriti Banka, Tanuja Chintada, Venkata Triveni, Manish Mehta 等

This position paper argues that the machine learning community should prioritize early-stage quality assurance in annotation pipelines over the prevailing practice of late-stage validation. Data quality bottlenecks increasingly limit foundation model improvement, yet quality assurance research focuses almost exclusively on validation methods rather than validation timing. *When* validation occurs—not merely *what* validation methods are employed—fundamentally determines both error rates and annotation costs. This temporal neglect is puzzling given the well-established "shift-left" principle from software engineering, where empirical studies demonstrate 4–100× cost multipliers for defects detected in later development stages (Boehm, 1981; Shull et al., 2002). Annotation pipelines, we argue, exhibit analogous dynamics: errors caught before annotation begins cost a fraction of those discovered after review cycles complete. We propose a taxonomy of three *QA trigger points*—pre-annotation (T₀), post-annotation (T₁), and post-review (T₂)—that decompose annotation workflows into discrete validation opportunities. A survey of 47 recent papers reveals that only 4% report when validation occurs, a striking gap given timing's demonstrated impact in adjacent fields. Without explicit attention to QA timing, the community risks optimizing validation methods while ignoring the structural variable that may matter most. We call on researchers to report QA timing configurations, on platform developers to expose timing as a first-class parameter, and on the community to conduct controlled experiments testing whether the shift-left principle transfers to annotation contexts.

Deep Learning · Generative Models and Autoencoders

Onkar Susladkar, Tushar Prakash, Gayatri Deshmukh, Kiet Nguyen, Jiaxun Zhang, Adheesh Juvekar, Tianshu Bao, Lin Chai, Sparsh Mittal, Inderjit Dhillon 等

We propose UniDFlow, a unified discrete flow-matching framework for multimodal understanding, generation, and editing. It decouples understanding and generation via task-specific low-rank adapters, avoiding objective interference and representation entanglement, while a novel reference-based multimodal preference alignment optimizes relative outcomes under identical conditioning, improving faithfulness and controllability without large-scale retraining. UniDFlow achieves SOTA performance across eight benchmarks and exhibits strong zero-shot generalization to tasks including inpainting, in-context image generation, reference-based editing, and compositional generation, despite no explicit task-specific training.

Deep Learning · Large Language Models

Canbin Huang, Tianyuan Shi, Xiaojun Quan, Jingang Wang, Jianfei Zhang, Qifan Wang

Model merging has emerged as a cost-effective approach for consolidating the capabilities of multiple LLMs without retraining. However, existing merging techniques, largely based on linear parameter arithmetic or optimization, struggle when applied to Mixture-of-Experts (MoE) architectures. We identify a critical failure mode in MoE merging, termed *routing breakdown*, in which the merged router fails to dispatch tokens to suitable experts. Routing breakdown stems from the sensitivity of the non-linear softmax and discrete Top-$k$ routing mechanisms to parameter perturbations from merging, a sensitivity further amplified by load-balancing constraints imposed during MoE pretraining. Because fine-tuned experts exhibit distinct specializations, even modest misrouting can cause severe performance degradation. To address this issue, we propose Hessian-Aware Router Calibration (HARC), a training-free framework that leverages second-order curvature information to realign the merged router. This approach admits a closed-form solution that can be efficiently solved using a matrix-free conjugate gradient method. Experiments on mathematical reasoning and code generation tasks show that HARC effectively mitigates routing breakdown across diverse MoE merging baselines and leads to substantial performance improvements.