NeurIPS 2026 论文列表

Diffusion Large Language Models (DLMs) are being actively explored as promising alternatives to autoregressive models due to their fast and flexible generation capabilities. To optimize inference in DLMs, recent studies have proposed a variety of decoding algorithms. However, the tendency of these methods to mimic autoregressive generation limits the speed and flexibility of DLMs, while also preventing the methods from fully realizing their potential. Moreover, this rigid approach leads to error propagation, while existing sampling-based correction methods incur prohibitive computational costs. To overcome this, we propose Renoise Consistency, a novel post-hoc approach that enables effective self-correction by maximizing train--inference consistency and can be applied to any decoding algorithm with a flexible computational budget. Furthermore, we introduce Adaptive Block Drafting, which leverages consistent internal representations of DLMs to significantly reduce the overall computational cost. When combined, our proposed method achieves up to a 9.00\% performance improvement over the semi-autoregressive baseline, along with a 25.85\% reduction in forward steps.

Generative solvers for combinatorial optimization benefit from additional test-time compute when their refinement states remain aligned with task relaxations. We introduce RAGenCO, a relaxation-aligned test-time scaling framework for generative combinatorial optimization. The central idea is to treat projection onto a task relaxation as a state control primitive: refinement first maintains a projected control state, and only then forms the task-dependent decoder input or expands candidates. For TSP and ATSP, Sinkhorn projection aligns matrix states with the cycle-cover relaxation during refinement and decoding. For MIS and MVC, Bernoulli projection controls refinement on the independent-set side, while raw logits are retained for terminal greedy decoding because their ordering carries the decoder signal. Best-of-$B$ branching then reallocates compute by expanding candidates around aligned control states rather than sampling from unconstrained logits. Because these operations are used only at inference, the diffusion training objective remains unchanged. Under equal runtime budgets, this alignment of control state, decoder input, and branching yields a strong quality-runtime trade-off on TSP and ATSP and competitive results on MIS and MVC.

Diffusion and flow-matching models scale because pretraining simply regresses against a closed-form target built by analytically noising clean data samples. In many settings, only a reward function is available, scoring how desirable a generation is, so training must proceed online from a pretrained model. Existing methods either rely on costly SDE rollouts, sometimes with reward gradients, or adopt heuristic reward-dependent variants of the pretraining objective. Under a stochastic optimal control formulation of KL-regularized reward maximization, the optimal generative process tilts only the clean-endpoint distribution and leaves the conditional noising law unchanged. Combining this path-space characterization with the adjoint-matching optimality condition and a REINFORCE estimator to avoid reward gradients, we derive Reinforce Adjoint Matching (RAM). At each step, we draw a clean endpoint from the current model with any off-the-shelf sampler, evaluate its reward, noise it to several training states, and regress against a closed-form, reward-weighted target. Like the pretraining objective, RAM is simple and scales. On Stable Diffusion 3.5M, RAM achieves the highest reward on composability, text rendering, and human preference. It is much more training efficient, reaching Flow-GRPO's peak GenEval accuracy in~$50\times$ fewer training steps.

Recent advances in generative modeling have enabled the efficient computation of Schrödinger bridges (SB) in high-dimensional settings by leveraging partially simulation-free training methods inspired by flow matching. However, these have not covered SBs with reflecting dynamics, a useful model choice with built-in guarantees that generated samples stay in the data domain. Existing alternatives for reflected SBs instead rely on more complex training based on forward--backward SDE theory, requiring expensive higher-order derivatives and sampling entire paths during training. In this article, we introduce a partially simulation-free framework that allows reflected SBs to be trained similarly to flow matching, using a new sampling method and regression target. We demonstrate our results by coupling pairs of well-known high-dimensional image datasets. Using reflected dynamics incurs negligible additional wall-clock time during both training and inference while maintaining or slightly improving generative performance.

Recursive training of generative models on their own outputs can lead to model collapse, a compounding drift away from the true data distribution. Existing theoretical works bound finite-round error accumulation in the context of diffusion models, but two questions remain open:~what distribution does the recursion converge to, and how fast? We answer both, isolating a mechanism distinct from imperfect learning: even with perfect score estimation and exact sampling, the early stopping of the reverse diffusion (required for numerical stability) drives a progressive drift away from the data distribution. We prove that this recursion converges geometrically to a unique limiting distribution, which admits a closed-form characterization as an infinite mixture of increasingly Gaussian-smoothed versions of the data distribution. A Hermite spectral decomposition of this limit reveals that recursive training acts as a low-pass filter: higher-order modes, which encode fine non-Gaussian structure, are attenuated much more strongly than coarse modes. This spectral picture motivates annealed truncation schedules that progressively shrink truncation times across retraining rounds; we prove that any schedule converging to $0$ asymptotically eliminates recursive compounding. Finally, we show our idealized characterization is robust: in the presence of discretization and score estimation errors, the learned distribution remains in a Wasserstein-2 ball around the ideal limit, with mode-dependent contraction rates that contract high-order errors faster than low-order ones. We validate the theory on synthetic Gaussian mixtures and CIFAR-10.

Frontier reasoning models are produced by post-training base language models with reinforcement learning. Recent work has challenged this by showing that sampling from a sharpened version of the base model's distribution, a so-called *power distribution,* elicits comparable reasoning without additional training, curated datasets, or verifiers. However, making this method practical requires *efficiently sampling* from the power distribution. A sampler needs to "mix" to the power distribution which necessitates moving between modes of the target distribution; intuitively, e.g., trying different reasoning strategies. The samplers proposed in prior works repeatedly select a "cut" position in the current reasoning trace uniformly at random and resamples the suffix from that position onwards. However, reasoning traces typically contain a few consequential decisions (e.g., the choice of proof strategy or algorithm), and we observe that a uniformly chosen cut tends to rewrites local details rather than revisiting decision points. We introduce an algorithm (Entropy-Cut Metropolis--Hastings) which uses the base model's next-token entropy as a proxy to identify key decision points and re-sample from these positions. We empirically verify that entropy jumps are a useful proxy for decision points, and in a stylized model of reasoning prove that our method's mixing time scales with the number of decisions in a trace rather than with the number of tokens, which can be much larger. Across MATH500, HumanEval, GPQA, and AIME on several models, our method consistently improves over baselines and RL-trained models.

Event sequences are chains of random events, each described by heterogeneous (numerical and categorical) features. The problem of event sequence forecasting occurs in finance, healthcare, business process intelligence, and other fields. In this work, we study long-horizon forecasting of event sequences as a conditional generative modeling problem. We evaluate forecast quality from two perspectives: prediction accuracy and distributional realism. To support this, we present a benchmark that contributes metrics for both aspects, strong statistical baselines, recent generative models adapted from adjacent fields, and curated real-world datasets. Careful evaluation reveals that no method excels at both accuracy and realism, highlighting a fundamental trade-off between the two. Finally, we introduce a procedure that aggregates samples from a realism-strong generative model into a state-of-the-art predictor, demonstrating that distributional realism can be converted into prediction accuracy.

Real-world television and streaming pipelines often deliver compressed HD video to increasingly capable displays, making video super-resolution (VSR) both practically important and fundamentally ambiguous. Existing generative VSR methods are largely receiver-only, requiring the model to infer missing high-frequency structures from degraded pixels alone. We propose MetaVSR, a sender--receiver collaborative framework that transmits compact structural edge metadata as bitrate-constrained side information for generative VSR. MetaVSR builds on a one-step video diffusion transformer and encodes both the low-quality video and transmitted metadata through the native 3D VAE, enabling token-level fusion within the original DiT attention blocks without additional control branches. We further introduce a rate-aware Canny edge metadata selection strategy that allocates metadata bits to structurally challenging regions, and evaluate reconstruction quality under matched total transmission budgets that include both compressed video and metadata. Across five public VSR benchmarks, MetaVSR shows that budgeted sender-side structural metadata can improve reconstruction over the receiver-only DOVE-5B baseline, increasing PSNR by 1.03 dB and SSIM by 0.055 on average while using a smaller 2B backbone. On MetaSPS, our rate--distortion evaluation shows approximately 20\% rate saving under light-noise degradation and more than 50\% under heavy-noise degradation compared with a no-metadata generative baseline. These results demonstrate that compact sender-side edge metadata can reduce reconstruction ambiguity and improve bitrate-efficient VSR when its transmission cost is explicitly accounted for.

Masked Autoencoders (MAE) have emerged as a powerful self-supervised paradigm in vision, yet their direct application to radar perception remains bottlenecked by a fundamental domain gap. Specifically, while conventional MAEs are optimized for RGB images using isotropic grid patching and standard mean squared error (MSE) loss, radar range-azimuth (RA) heatmaps exhibit sinc-oriented anisotropic spatial structures as well as complex physical artifacts, such as heavy-tailed multipath interference and sidelobe spikes. In this paper, we propose RadarMAE, the first radar-centric MAE tailored specifically to the physical properties of radar signals. We present an axial tokenization strategy that preserves the resolution disparities and continuous sinc-shaped lobes of RA maps. Furthermore, considering that the range and azimuth dimensions exhibit distinct physical artifacts, we decouple their reconstruction objectives by introducing a multipath distribution loss along the range axis to capture heavy-tailed multipath reflections as well as a sidelobe distribution loss along the azimuth axis to learn deterministic sidelobe spikes. Our extensive experiments demonstrate that injecting these domain-specific physical priors enables robust representation learning for radar object detection. Notably, our method achieves a state-of-the-art 64.17% bird's-eye-view (BEV) AP on the K-Radar dataset using only a single-frame RA map setting, significantly outperforming the previous baselines.

The Maximal Independent Set (MIS), Dominating Set (DS), and Vertex Cover (VC) problems are fundamental combinatorial optimization problems with wide-ranging applications. We identify a key property of these problems: by finding a cut in the graph and determining the states of vertices associated with the cut, the graph can be decomposed into multiple subgraphs whose solutions are independent of each other. Therefore, we classify MIS, DS, and VC as Edge-Cut Separable Problems (ECSPs). This property enables a natural divide-and-conquer strategy, which significantly reduces the computational complexity and allows neural networks to scale to large-scale graphs that were previously intractable. Based on this property, we propose a recursive framework that leverages this property to approximately solve ECSPs, namely \ours. Our framework consists of two major components: a partitioner that identifies a cut in the graph, and a predictor that solves the cut-determination sub-problem (CDSP) to determine the states of vertices associated with the cut. By recursively applying these components, RGF generates a complete solution for the original ECSP instance. Additionally, through partial prediction, the memory consumption is significantly reduced, enabling RGF to handle real-world large graphs. Experimental results validate the advantages of RGF: the performance of our method is up to 2.13\% better than the state-of-the-art machine learning (ML)-based approach, and our approach can handle real-world large graphs with up to 11M vertices.

Generative models can produce images nearly indistinguishable from real data, yet rigorous and interpretable evaluation remains challenging. Conventional metrics such as FID provide only scalar scores with limited diagnostic insight. Widely adopted CLIP-based metrics enable semantic evaluation beyond simple training class labels, but inherit limitations from CLIP’s training paradigm that restrict attribute-wise analysis. We propose RA-CLIPScore, a novel metric that mitigates these issues and extends CLIP-based evaluation to spatial distribution alignment, measuring whether generated objects adhere to the positional priors found in the training data. RA-CLIPScore introduces dual prompts to decouple competing attributes and leverages local patch tokens to capture fine-grained regional semantics. We evaluate image generative models on their ability to match both attribute and spatial distributions of the training data. Extensive experiments show that RA-CLIPScore provides more robust and interpretable evaluations than prior methods, particularly under distribution misalignment or partially irrelevant textual attributes. We further demonstrate how it reveals previously undocumented regional tendencies in generative models.

Diffusion models dominate visual generation, but iterative denoising remains computationally demanding, especially under Classifier-Free Guidance (CFG), which is crucial for high-fidelity generation yet nearly doubles per-step computation. To reduce this burden, recent training-free caching methods reuse intermediate predictions during sampling, yet their single-prediction criteria are misaligned with CFG sampling, where the denoising update is governed by the guided prediction rather than either branch alone. Consequently, such reuse may misestimate the error that actually perturbs sampling, leading to a **branch-guided mismatch**. Moreover, due to error propagation across timesteps, a local guided error may not faithfully reflect the final deviation, inducing a **local-final mismatch**. To address these two mismatches, we propose **RA-CFGCache**, a **R**isk-**A**ligned **Caching** framework for CFG. **RA-CFGCache** introduces CFG-aware Guided-Risk Composition to align caching decisions directly with the guided prediction, and Propagation-Aware Rescaling to calibrate local guided risks against the final generative deviation. Extensive experiments on FLUX.1-dev, Wan2.1-T2V-1.3B, and CogVideoX-2B show that **RA-CFGCache** delivers superior efficiency-fidelity trade-offs over existing training-free caching methods. Moreover, **RA-CFGCache** is compatible with diverse caching strategies and can further enhance their fidelity, e.g., improving PSNR over MagCache from 21.46 to 24.02 under CFG. The code is available at https://anonymous.4open.science/r/RA-CFGCache/.

Generative recommendation has recently emerged as a promising paradigm for large-scale recommendation by reformulating next-item prediction as discrete sequence generation. However, current SID-based models rely mainly on history-to-next-item supervision, leaving item--item collaborative topology only indirectly captured through sparse user sequences. To address this gap, we propose *R-GRec*, a graph-derived structural supervision framework for SID-based generative recommendation. From user interactions, *R-GRec* builds an item--item graph and derives three complementary auxiliary objectives---Neighbor Prediction, Topological Contrast, and Link Prediction --- to make collaborative topology explicit during generative training. Extensive experiments on the two public Amazon datasets demonstrate that R-GRec achieves state-of-the-art performance over representative traditional, generative, and LLM-based recommenders. Further ablation and analytical studies verify the contribution of each graph-derived objective and show that collaborative topology acts as a complementary supervision signal to Semantic ID generation, improving generative recommendation without adding inference-time graph computation.

We introduce a framework for learning distributions supported on manifolds based on estimating the projection onto the underlying data manifold. Specifically, we define an objective functional over a class of functions whose minimizer recovers this projection. The proposed framework automatically adapts to the intrinsic dimension and allows for data supported on unions of manifolds with varying dimensions. The resulting objective can be optimized using standard neural network architectures. We present population-level results establishing recovery of the manifold projection and prove finite-sample Wasserstein generalization bounds. Furthermore, we validate the approach empirically across a range of settings. In contrast to widely used generative models such as diffusion models, whose objectives can be minimized by memorizing training samples, our formulation penalizes such behavior. Thus, returning training data does not yield low loss. We also introduce a direct memorization metric to verify that the learned projection generates new samples rather than reproducing the training set.

Diffusion and flow-based generative models dominate visual synthesis, with guidance aligning samples to user input and improving perceptual quality. However, Classifier-Free Guidance (CFG) and extrapolation-based methods are heuristic linear combinations of velocities/scores that ignore the generative manifold geometry, breaking probability conservation and driving samples off the learned manifold under strong guidance. We analyse guidance through the continuity equation and show its effect decomposes into a divergence term and a score-parallel term defined invariantly across parameterisations. We prove the divergence term blows up structurally as sampling approaches the data manifold, motivating a time-dependent schedule alongside score-parallel attenuation. The resulting plug-and-play rule, Adaptive Manifold Guidance (AdaMaG), bounds both terms at no additional inference cost. Finally, we show that most empirical heuristics for reducing saturation or improving generation quality correspond directly to the two terms in our decomposition. Across image generation benchmarks, AdaMaG improves realism, reduces hallucinations, and induces controlled desaturation in high-guidance regimes.

Ante-hoc interpretability methods based on prototypes provide highly accurate explanations by utilizing the intuitive "this looks like that" reasoning paradigm. On the other hand, post-hoc models can explain predictions for a single image without relying on an underlying dataset or requiring costly neural network retraining. Recent approaches successfully solve the retraining problem for prototype-based networks. However, they still face a fundamental limitation: they require access to a subset of data (e.g., a test or validation set) to search for and extract the visual prototypes. In this paper, we address this issue and introduce ProDG: Data-Free Generative Prototypes for Post-Hoc Explainability, a novel framework that leverages generative models to synthesize pure, high-fidelity prototypes directly from the frozen model's weights, completely eliminating the dependency on any external data. By establishing this new frontier in Data-Free XAI, DGP unlocks robust visual interpretability for privacy-sensitive domains, where original data is strictly restricted or fundamentally inaccessible.

Deep bisimulation metric learning has emerged as a principled framework for learning robust state representations in reinforcement learning. However, prevailing methods rely on sample-based regression objectives that exhibit a critical stability flaw in stochastic environments. We identify this flaw as a manifestation of the **double sampling problem**: minimizing mean squared error against single-sample stochastic targets introduces an irreducible variance bias. Through the lens of stochastic differential equations (SDEs), we rigorously prove that this bias leads to a **Variance Trap**, wherein target variance scales with the encoder's sensitivity. This variance effectively acts as an implicit Jacobian regularizer, driving representation collapse in the presence of transition noise. To address this issue, we propose Bisimulation Saddle-Point Optimization (BSPO), a debiased framework that reformulates the bisimulation metric learning objective as a primal-dual saddle-point problem. By introducing an Auxiliary Network (AuxNet) to estimate the expected Bellman error, BSPO decouples the structural error from transition noise, eliminating the bias without requiring physically infeasible double sampling. To the best of our knowledge, this work is the first to identify that prevailing sample-based bisimulation metric learning objectives are systematically biased and to provide a practical debiasing framework. Our empirical evaluations on stochastic continuous/discrete control tasks and visually distracting environments demonstrate that BSPO significantly outperforms representative baselines, particularly in high-noise regimes where conventional methods fail to converge.

Predicting protein dynamics is a long-standing problem in computational structural biology. Often, protein function critically depends on local directed motions, such as hinge movements, catalytic loop rearrangements and domain reorientations, which can be characterized by directional flexibility and correlated structural motions of the protein backbone. While Molecular Dynamics (MD) simulations provide an established but often prohibitively expensive approach, recent deep generative models aim to reduce this cost by directly predicting conformational ensembles, emulating MD. However, due to their large size and the need to generate several states until the derived dynamical properties converge, these models remain expensive. In this work, we propose a fast SE(3)-equivariant graph neural network to directly predict dynamical descriptors, such as directional backbone flexibility and pairwise dynamic correlations, from an equilibrium structure. In a series of experiments, we show that our model matches the accuracy of substantially larger ensemble generation models while being orders of magnitude faster, and demonstrate that the proposed equivariant architecture is especially well-suited for capturing anisotropic motions in proteins.

Diffusion models cannot enforce hard constraints, yet applications in the physical sciences demand exact satisfaction of conservation laws, boundary conditions, and observational consistency. In this work, we identify a corrector kernel whose unique stationary distribution is the constrained marginal at each noise level, and approximate it by iteratively projecting through the denoiser and renoising via the forward kernel. The resulting Predict-Project-Renoise (PPR) algorithm enables sampling from pretrained diffusion models under hard constraints. Its three components are each necessary: projecting through the denoiser keeps samples close to the data manifold, while renoising and iterating drive samples toward the constrained marginal. On 2D distributions, the Kuramoto-Sivashinsky equation, and global weather forecasting with a $10^8$-dimensional atmospheric model, PPR simultaneously achieves low constraint violations and high distributional fidelity, a combination that existing methods fail to deliver.