NeurIPS 2026 论文列表

Generative models are increasingly used to solve scientific inverse problems, but existing evaluations still focus primarily on whether a method can produce a single plausible reconstruction. This is insufficient for ill-posed problems, where multiple solutions may be consistent with the same sparse or noisy observations. In these settings, a method can achieve strong pointwise accuracy while still failing to capture the true posterior through mode collapse, over-confident uncertainty, or averaging incompatible solutions. We introduce PosteriorBench, a benchmark for evaluating the distributional accuracy of generative inverse solvers. PosteriorBench evaluates four physics-based inverse problems: Darcy flow inversion, Poisson source recovery, carbon capture and storage, and light transport material inference. For each task, we construct high-fidelity reference posteriors using slow but established procedures such as rejection sampling and Markov chain Monte Carlo, enabling direct assessment of whether solvers recover the full set of solutions rather than the single best sample. The benchmark spans sparse sensing, low-resolution observations, nonlinear forward models, varying noise levels, and multimodal priors, with a unified pipeline for distribution matching, uncertainty quantification, and hyperparameter calibration. Our experiments reveal substantial distribution-matching gaps across current solvers, while showing that neural operators improve resolution robustness and that guidance weights and generation noise are key to posterior-variance calibration.

Transformer models have demonstrated a remarkable ability to perform a wide range of tasks through in-context learning (ICL), where the model infers patterns from a small number of example prompts provided during inference. However, empirical studies have shown that the effectiveness of ICL can be significantly influenced by the order in which these prompts are presented. Despite its significance, this phenomenon has been largely unexplored from a theoretical perspective. In this paper, we theoretically investigate how positional encoding (PE) affects the ICL capabilities of linear attention transformer models, particularly in tasks where prompt order plays a crucial role. We examine two distinct cases: linear regression, which represents an order-invariant task, and dynamical systems, a classic time-series task that is inherently sensitive to the order of input prompts. Theoretically, we evaluated the change in the model output when two types of positional encoding (one-hot and RoPE) is incorporated and the prompt order is altered. In all cases, the leading dependence on the permutation size and context length is $k/N$, with constants determined by the positional encoding, model weights, input dimension, and task dependent parameters. These theoretical findings are experimentally validated.

This position paper argues that the research community must act to maintain research pipeline reliability despite increasing threats from GenAI. We start in the pre-GenAI era by highlighting some of the prominent critiques of the research pipeline, consisting of: (a) Authoring, (b) Reviewing, and (c) Evaluating researchers based on bibliometrics. Then, we discuss some of the effects GenAI has had on each research pipeline component based on the best available data, limited though it may be. Importantly, due to opaqueness of the submission pipeline, it is difficult to measure both the impact of GenAI and the efficacy of interventions, which leads us to call for greater transparency. Last, we conclude by offering three alternative views and ten paths forward that may mitigate some of the issues we highlight by keeping human researchers as the primary driver of science

The ability of neural networks to generalize is fundamentally shaped by their computational units. While the perceptron provides a first-order, linear inductive bias and the radial basis function (RBF) unit offers an isotropic curved bias, we identify a critical opportunity for a structured extension: the Generative Matching Unit (GMU). Each individual GMU captures complex dependencies by treating the forward pass as an inference problem; its internal generative model optimizes instance-specific latent parameters to compute a reconstruction error, effectively measuring a point-to-manifold distance as opposed to the point-to-point distance in RBFs. We focus on linear GMUs, which yield closed-form analytical expressions for fast computation and extend naturally to convolutional architectures. Our theoretical analysis demonstrates that linear GMUs are highly flexible universal approximators capable of recovering structured class posteriors. We prove that while a single GMU can exactly emulate an RBF kernel and two can emulate the decision boundary of a perceptron, emulating a single $k$-order GMU’s decision boundary requires a hidden layer of standard units that scales polynomially or exponentially with input dimensionality. Furthermore, we prove that the GMU’s point-to-manifold distance remains discriminative in high dimensions where standard Euclidean distances fail, offering unique robustness to the curse of dimensionality. Finally, we show that GMUs offer superior flexibility and efficiency in learning smooth manifold decision boundaries compared to MLPs and RBFs. Motivated by the theoretical results, we place GMUs in the first network layer like RBFs, where their role is to enhance linear separability for subsequent layers. This avoids the typical gradient collapse problem with stacking RBF-like units while ensuring the generalization benefits remain. We find that across extensive experiments involving 27 tabular datasets, five vision datasets evaluated across 34 test-time corruption settings, and 30 synthetic scenarios, GMU networks demonstrate statistically significant improvements in generalization and robustness.

Plug-and-Play (PnP) methods with generative priors have achieved strong performance in inverse problems, with recent flow matching models enabling fast and scalable reconstruction. However, a key challenge in PnP methods is maintaining consistency between data fidelity updates and the learned generative prior, as data-consistency steps can move iterates away from the flow trajectory. We propose an ADMM-based PnP framework for flow matching priors that enforces stronger consistency between the measurement model and the prior through auxiliary variables and dual updates. In addition, we introduce a trajectory correction mechanism that restores consistency with the flow via a combination of deterministic and stochastic projections. Our method provides a more principled integration of flow priors within PnP frameworks, achieving high-quality reconstructions with reduced computational cost.

Most world models for future prediction prioritize aestetic quality of generated videos, but offer only weak physical grounding and limited geometric consistency over time, due to the lack of explicit 4D modeling. In this paper, we introduce plan4d, a possible next milestone towards building a generative plannable 4D world model that predicts future RGB videos together with dense 4D geometry, including depth, cameras, point clouds, and scene flow from an observed scene context and text-specified actions. Since training data with paired actions and dense 4D annotations is inherently scarce, plan4d leverages the complementary priors of foundational video generators and 3D reconstructors. Specifically, we propose a model-stitching architecture that couples Depth Anything 3 with LongCat-Video and augments it with an auxiliary DPT head for scene-flow prediction. The resulting model allows us to plan and generate complex, long-horizon, and fine-grained actions in a dynamic 3D scenes, while substantially improving both visual fidelity and geometric accuracy of the generated future videos. Extensive experiments on both synthetic and real-world datasets demonstrate that plan4d achieves state-of-the-art performance in generative 4D modeling of environmental reactions.

Most practical high-resolution text-to-image systems rely on latent diffusion models, where generation is performed in a compact latent space and a decoder maps latents back to pixels. Yet the latent-to-pixel decoder in this pipeline remains primarily reconstruction-oriented: as the sole pathway from latents to pixels, it is optimized to invert an encoder rather than to synthesize high-resolution details, and becomes increasingly costly in megapixel pipelines. This gap calls for a more expressive and efficient decoding paradigm. Motivated by recent progress in scalable pixel-space diffusion, we introduce **PiD**, a **Pi**xel diffusion **D**ecoder that reformulates latent decoding as conditional pixel diffusion, unifying decoding and upsampling into one generative module. By denoising directly in high-resolution pixel space, PiD synthesizes $4\times$and even $8\times$ upscaled images with low latency. For latent conditioning, a lightweight sigma-aware adapter injects noise-corrupted latents into the backbone, enabling PiD to handle partially denoised states and terminate the base diffusion process early. To further improve efficiency, we distill the decoder using DMD2, reducing inference to just $4$ steps. PiD applies to both conventional VAE latents and semantic latents (e.g., SigLIP, DINOv2) used in recent RAE-based models. Across multiple latent spaces and base generators, PiD improves visual fidelity over conventional decode-then-upsample cascades while reducing memory and latency, decoding latents of $512{\times}512$ images into $2048{\times}2048$ pixels in under $1$ second with $13$ GB peak memory on a consumer RTX 5090, and as fast as $210$ ms on a data-center GPU, about $6{\times}$ faster than cascaded diffusion-based super-resolution pipelines.

Generating dance that reflects many aspects of music remains a fundamental challenge in dance motion synthesis. Existing music-conditioned approaches formulate the task as beat-level matching, which captures local synchrony but misses the compositional structure of rhythm, where movement is organized into global beat units. We argue that musical dance arises from the alignment of \emph{periodicity} between motion and music, not from instantaneous beat coincidence. To address this, we propose \textbf{PhaseDance}, a phase-conditioned framework that represents dance as a quasi-musical signal on periodic phase manifolds, enabling unified dance generation across multiple tasks. Alongside this, we ground text descriptions in fifteen music-correlated metrics derived from Laban Movement Analysis to capture the qualitative richness of dance, articulating structured dimensions of motion — effort, shape, and dynamics — that coarse genre labels cannot convey. Experiments show that PhaseDance produces choreography with stronger rhythmic coherence and richer expressive understanding than existing models.

Dense associative memory underlies modern attention mechanisms; however, conventional Modern Hopfield Network (MHN) with linear kernels yields overlapping attractor basins and spurious states under high memory load, limiting their theoretically exponential storage capacity in practice. We construct a class of nonlinear phase kernels that reshape the energy dynamics into deep, well-separated basins, and prove that any kernel in this class preserves exponential storage capacity while guaranteeing convergence to fixed points. As a representative instantiation, we introduce the Sigmoidal Phase Hopfield Network (S-Hop), which guarantees monotone energy descent and mitigates the practical loss of memory capacity. Experiments on MNIST and CIFAR-10 show that S-Hop achieves up to a $50\times$ increase in critical capacity over baseline models. We also provide a systematic capacity measurement of Hopfield networks on TinyImageNet, where S-Hop exhibits improved retrieval robustness and noise resilience. The phase-kernel design provides a principled route toward more robust dense associative memory.

Diffusion models are central to generative modeling and have been adapted to graphs by diffusing adjacency matrix representations. The challenge of having up to $n!$ such representations for graphs with $n$ nodes is only partially mitigated by using permutation-equivariant learning architectures. Despite their computational efficiency, existing graph diffusion models struggle to distinguish certain graph families and their spectra, unless graph data are augmented with ad hoc features. This shortcoming stems from enforcing the inductive bias within the learning architecture. In this work, we leverage random matrix theory to analytically extract the spectral properties of the diffusion process, allowing us to push most of the inductive bias from the architecture into the dynamics. Building on this, we introduce the Dyson Diffusion Model, which employs Dyson's Brownian motion to capture the spectral dynamics of an Ornstein-Uhlenbeck process on the adjacency matrix. Furthermore, conditioned on the spectral dynamics, we formulate a Lie group diffusion, appropriately modeling the remaining degrees of freedom. Strikingly, the resulting learning problem becomes permutation invariant at the Lie algebra level. We demonstrate that the Dyson Diffusion Model learns graph spectra accurately and outperforms existing graph diffusion models.

Flow Matching is a powerful framework for learning transport maps between probability distributions. Yet its standard single-parameter formulation is not designed to capture multi-parameter variations where the resulting transport should be path-independent. Path independence is crucial because it ensures that transformations depend only on the initial and target distributions, not on the specific path. In this work, we introduce \textit{Path-independent Flow Matching (PiFM)}, a method for learning vector fields whose induced flows yield path-independent transport between distributions. We show that PiFM generalizes Flow Matching to higher-dimensional parameter domains while enforcing structural conditions that ensure consistency of composed transformations. In addition, we show that, under suitable assumptions, PiFM approximates the Wasserstein barycenter, linking the framework to a notion of distributional interpolation. To enable practical training, we propose a tractable, simulation-free objective that regresses onto multi-parameter conditional probability paths. We showcase empirically that PiFM outperforms other approaches on both synthetic and real world data in interpolating path-independent trajectories and generating desired out of distribution samples. Our code is available at \url{https://anonymous.4open.science/r/Pi_flow_matching-C83F/}.

Probabilistic circuits (PCs) have emerged as generative models guaranteeing tractable probabilistic inference. However, tractability comes at the price of larger model sizes than in other neural generative models. As such, to scale PCs to high-dimensional data such as images, previous work has devised several parameter sharing techniques as well as fast evaluation protocols that consider learning PCs on independent image patches. In this work, we revisit this practice to highlight a surprising learnability issue: models that assume independence counterintuitively can yield better likelihoods than models that do not. To break this apparent bottleneck and to scale PCs further, we introduce a recursive parameter sharing construction (RePA) that fosters efficiency without assuming independence. In a set of rigorous experiments, we show that RePA can greatly reduce time and memory consumption while yielding competitive likelihoods.

An LLM safety patch can pass a benchmark while still being a poor repair. This risk is especially acute for jailbreak repairs, where the goal is to correct a specific unsafe behaviour without changing unrelated behaviours. A patch may block the exact prompts used for evaluation yet fail on close harmful variants, or suppress harmful behaviour by over-refusing benign prompts that share its wording or structure. Existing evaluation protocols primarily test whether models can be broken, while aggregate metrics, such as attack success, refusal rates, and global capability scores, cannot distinguish selective repairs from broader local suppression. To address this gap, we introduce **PatchBench**, a benchmark of empirically observed model-specific jailbreak failures that induce actionable harmful answers, designed as concrete repair targets for patching research. Starting from 27,870 prompts aggregated from 37 public jailbreak benchmark datasets, we manually curate 15,314 English prompts and query 8 open-source instruction-tuned models. We then combine WildGuard filtering, pairwise Elo ranking, and manual verification to retain only unsafe completions that answer the harmful requests. The result is a curated bank of 400 high-confidence jailbreak failures, organised by model. We further introduce **PatchBench-Local**, a local evaluation protocol that tests whether a patch is behaviourally precise. For each harmful source prompt, PatchBench-Local generates three families of local neighbours: harmful variants that preserve the malicious intent, benign prompts with matched structure, and benign prompts that reuse the key harmful terms. It evaluates both harmful-neighbour correction and benign-neighbour preservation, thus distinguishing selective repair from broader local suppression. We use PatchBench-Local and MMLU to evaluate four state-of-the-art activation steering methods. Our results show that global capability can remain nearly unchanged while local benign-neighbour regressions are severe, confirming that aggregate metrics alone can miss important collateral damage. By exposing whether patches act as precise behavioural repairs or as broad local suppressors, PatchBench-Local provides a more precise basis for developing and comparing jailbreak repair methods.

Preference ranking modeling is important for selecting and adapting language-model responses to human preferences. Compared with deterministic ranking methods, generative preference ranking models the prompt-response data distribution, providing richer uncertainty characterization and sample diversity for learning a more expressive ranking boundary. Recent work improves modeling efficiency by shifting generative preference ranking from textual space to embedding space, but without explicit preference-conditioned separation, the learned embedding distribution may still entangle preferred and rejected responses, producing ambiguous synthetic samples that weaken the ranking boundary. To address this issue, we propose PRISM, a Preference Ranking framework through dISentangled embedding Modeling. PRISM formulates embedding-level generative preference ranking with a unified class-conditional ELBO and decomposes this optimization objective to expose the encoded latent entanglement between preferred and rejected embeddings. This derivation motivates two practical preference-aware generation variants: PRISMMI, involving a deep class-separation objective, and PRISMMMD, catering a probabilistic aggregate-matching objective. Both variants learn a preference-disentangled embedding data distribution and synthesize data pairs that preserve ranking semantics for the generative ranking boundary. Experiments show that PRISM improves preference ranking performance and produces useful generated embeddings for downstream response selection. The anonymous code repository is available at:https://anonymous.4open.science/r/PRISM-915C/README.md.

Generative AI models now produce images indistinguishable from real data, making publicly verifiable provenance essential; however, existing watermarking methods become vulnerable to forgeries and adversarial optimization attacks once their detectors are made public. We propose PP-Mark, a provenance framework that anchors lightweight statistical detection to a zero-knowledge proof of the embedding process, ensuring that forged content cannot pass full verification by construction. We establish formal unforgeability under standard cryptographic assumptions and validate PP-Mark against representative baselines across two architectures, demonstrating resistance to black-box imprint forgery, white-box optimization, and regeneration attacks while remaining practical for decentralized verification.

Diffusion image generators owe much of their practical success to accurate denoising networks and strong numerical samplers. Yet the two components are not fully matched. During sampling, the denoiser is asked to make predictions based on imperfect noisy states formed by model predictions that differ from the training noisy states formed by real data. This train-test gap, known otherwise as exposure bias in literature, caps image generation quality (i.e., blurry, lacking in details or unnaturally-shaped). To mitigate the problem, we propose PEEK, a training-free deterministic sampler plugin. At each eligible denoising step, PEEK first performs a provisional one-step update, evaluates the denoiser once at the look-ahead state, and either keeps the current clean prediction or replaces it with this one-step-later prediction to form the actual noisy state. By taking the additional step, we generally obtain a higher-signal, more-image-like prediction for the noisy state, mitigating the exposure bias. To optimize the replacement positions, PEEK searches for a binary replacement schedule with a greedy metric-driven search made efficient by the PEEK prefix and baseline noise-schedule-rebasing caches; for a 9-step search, the caches reduce the one-candidate worst-case vanilla denoiser-evaluation count by 69.3\%. Across pixel-space and latent-space diffusion models with unconditional, label-guided, and text-guided settings on CIFAR-10, CelebA-HQ, LSUN Bedroom, ImageNet, and MS-COCO datasets, PEEK improves over NFE-matched DPM-Solver++ and DEIS baselines, with five-run mean FID reductions up to 39.3\% under the same deployment cost. Code will be released.

Full-duplex spoken language models (FD-SLMs) enable seamless speech interaction by allowing models to listen and speak simultaneously, yet the internal mechanism by which they coordinate listening and speaking remains underexplored. We analyze the predictive behavior encoded in FD-SLM hidden representations and find that they exhibit stream-specific predictive patterns: during listening, they preferentially predict the incoming user stream, whereas during speaking, they preferentially predict the model-side output stream. Building on this observation, we show that FD-SLMs dynamically modulate their internal predictive focus between two states: a generative state aligned with model-side output generation and a perceptive state aligned with incoming user input. However, this modulation can lag behind abrupt changes in conversational context. During user interruptions, the model remains transiently biased toward the generative state before transitioning into the perceptive state, causing it to miss the beginning of the incoming input. We term this delayed internal transition state inertia. To quantify its downstream impact, we introduce the Zero-Buffer Benchmark (ZBB), a diagnostic benchmark for evaluating immediate interruption comprehension when user speech begins abruptly. We evaluate this setting using response correctness and initial-word occurrence rate (IWOR). Finally, we mitigate state inertia through activation steering with a perception vector, a training-free intervention with little additional computational overhead. Across multiple state-of-the-art FD-SLMs, activation steering substantially improves interruption handling; for example, on PersonaPlex, it improves correctness from 28% to 45% and IWOR from 40% to 72% without any fine-tuning.

Flow-based generative models have emerged as an efficient alternative to diffusion models. We study the sample complexity of learning a target distribution in Wasserstein distance via flow matching, which learns a velocity field transporting a base distribution to the target. Under standard assumptions on the network architecture and data distribution, we show that any squared-loss flow-matching variant including rectified flow with bounded derivatives achieves $\widetilde{O}(\varepsilon^{-2})$ sample complexity with the Wasserstein guarantee taking the form $W_2 \le K(\varepsilon + C\sqrt{\varepsilon_{app}})$, where $\varepsilon_{app}$ is the approximation error of the network class. This improves upon existing $\widetilde{O}(\varepsilon^{-4})$ guarantees and does not require the Polyak \L{}ojasiewicz condition assumed in prior work. Instead, we exploit a structural property of the squared-loss objective - it induces an approximate Bernstein condition that directly ties the variance of the excess loss to the excess risk up to additive approximation-error. This condition enables a localized Rademacher complexity analysis yielding fast $O(1/n)$ rates. The flow-matching schedule enters only through the Lipschitz constant of the pointwise loss, which we characterize explicitly for standard schedules.

We introduce SODA, a generalization of Optimistic Dual Averaging, which provides a common perspective on state-of-the-art optimizers like Muon, Lion, AdEMAMix and NAdam, showing that they can all be viewed as optimistic instances of this framework. Based on this framing, we propose a practical SODA wrapper for any base optimizer that eliminates weight decay tuning through a theoretically-grounded $1/k$ decay schedule. Empirical results across various scales and training horizons show that SODA consistently improves performance without any additional hyperparameter tuning.