NeurIPS 2026 论文列表

Training large text-to-image models requires high-quality, curated datasets with diverse content and detailed captions. Yet the cost and complexity of collecting, filtering, deduplicating, and re-captioning such corpora at scale hinder open and reproducible research in the field. We introduce MONET, an open *Apache 2.0* dataset of $103.8$M image–text pairs collected from 2.9B raw pairs across heterogeneous open sources through successive stages of safety filtering, domain-based filtering, exact and near-duplicate removal, and re-captioning with multiple vision-language models covering short to long-form descriptions, and further augmented with synthetically generated samples. Each image is shipped with pre-computed embeddings and annotations to accelerate downstream use. To validate the effectiveness of MONET, we train a 4B-parameter latent diffusion model *exclusively* on it and reach competitive GenEval and DPG scores, demonstrating that our dataset lowers the barrier to large-scale, reproducible text-to-image research.

Recent advancements in audio generation have been largely driven by Transformer-based diffusion models. However, these models suffer from quadratic complexity of self-attention, severely bottlenecking the long-form audio synthesis. To overcome this limitation, we propose MFlowAudio, a novel latent audio generation framework that synergizes the continuous-time dynamics of Flow Matching with a custom-designed TFMamba backbone. TFMamba uses an innovative dual-scan mechanism: a TimeMamba module to capture long-range causal dependencies with linear complexity, and a FrequencyMamba module to model spectral correlations such as harmonic structures. Exploiting this structural foundation, we formulate the Stateful Flow Matching (SFM) paradigm. This framework inherently enables chunk-wise training and streaming generation, maintaining an $\mathcal{O}(1)$ caching complexity without incurring extra computational overhead. To enable fine-grained controllable synthesis, we devise a novel guidance mechanism that neutralizes vector field collisions precipitated by on-the-fly semantic transitions of prompts. Comprehensive empirical evaluations confirm that MFlowAudio yields generative fidelity on par with state-of-the-art baselines while establishing significant computational efficiency, achieving an $81.8$% acceleration in generation and facilitating perceptually seamless streaming synthesis with a constant, ultra-low latency of $1.8$ seconds. Demo:https://huggingface.co/spaces/mflowaudio/MFlowAudio

Spatio-temporal point processes (STPPs) represent a random collection of points where each point corresponds to the time and location of an event. STPPs are widely used to describe a wide range of phenomena, from earthquakes to wildfires to crime occurrence to disease outbreaks. Generative models have recently emerged as a new powerful paradigm for STPPs, demonstrating %due to their exceptional highly competitive generalization capabilities and promising potential for systematic uncertainty quantification. However, existing generative approaches primarily rely on unimodal numerical data, overlooking the geographic context in which events occur and failing to capture critical spatial and temporal patterns within the STPP. To address these limitations, we propose Morse-aware Cross-Modality learning within Diffusion Model, or \textbf{MCM-DM}. MCM-DM represents a cross-modality diffusion framework based on the discrete Morse and cobordism theories that augments STPP modeling with geographic scene understanding. MCM-DM consists of three key components: (i) a vision-language model-based geographic encoder that extracts semantic embeddings from satellite tiles at each event location; (ii) an attention-based fusion mechanism to integrate critical structure representation with spatio-temporal embeddings, and (iii) a Morse-theoretic topological aligner which aligns latent representations of critical events with spatio-temporal embedding space. We demonstrate the MCM-DM utility on 8 diverse STPP datasets from Earth sciences, epidemiology, urban mobility, and crime analytics, highlighting its cross-domain versatility. The code is available at~\url{https://anonymous.4open.science/r/MCM-DM-CF83}.

Block diffusion LLMs are an emerging paradigm for parallel language generation, but their KV caching makes memory access the dominant bottleneck in long-context inference. Sparse attention, which attends only to a small KV subset per query, can reduce this latency with minimal accuracy loss. In block diffusion, however, the $B$ tokens of each block must share a single KV subset, and we show this per-block constraint degrades existing sparse KV estimators by up to 25% in recall. We address this challenge by exploiting a property that emerges from the block-diffusion training objective: it aligns the block-average query across denoising steps, so the All-[MASK] block at the first step already reveals the per-block KV subset for the entire trajectory. We exploit this in MAGE ([MASK]-Guided Sparse Attention), a training-free method that runs one exact attention pass at the first step and reuses its top-$k$ index sets for all remaining steps within the block. Across three block-diffusion families on LongBench, MAGE matches Exact Attention at $k{=}512$ with near-lossless accuracy, achieves up to $6.82\times$ end-to-end speedup at $128$K context, and runs up to $3.35\times$ and $2.28\times$ faster than Quest and SparseD, designed for AR LLMs and fully bidirectional diffusion LLMs, respectively.

Generative real-world image super-resolution (Real-ISR) can synthesize visually convincing details from severely degraded low-resolution (LR) inputs, yet its stochastic sampling makes a critical failure mode hard to avoid: outputs may look sharp but be unfaithful to the LR evidence, exhibiting semantic or structural hallucinations. Preference-based reinforcement learning (RL) is a natural fit because each LR input yields a rollout group of candidate restorations. However, effective alignment in Real-ISR is hindered by three coupled challenges: (i) the lack of an LR-referenced faithfulness signal that is robust to degradation yet sensitive to localized hallucinations, (ii) a rollout-group optimization bottleneck where scalarizing heterogeneous rewards before normalization compresses objective-wise contrasts and weakens DiffusionNFT-style reward-weighted updates, and (iii) limited coverage of real degradations, which restricts rollout diversity and preference signal quality. We propose LucidNFT, a multi-reward RL framework for flow-matching Real-ISR. LucidNFT introduces LucidConsistency, a degradation-invariant and hallucination-sensitive LR-referenced evaluator trained with content-consistent degradation pools and original-inpainted hard negatives; a decoupled reward normalization strategy that preserves objective-wise contrasts within each LR-conditioned rollout group before fusion; and LucidLR, a large-scale collection of real-world degraded images for robust RL fine-tuning. Extensive experiments show that LucidNFT improves perceptual quality on strong flow-based Real-ISR baselines while generally maintaining LR-referenced consistency across diverse real-world scenarios.

Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models for language modeling, yet the effective design of transformer architectures for MDMs remains underexplored. In this paper, we show that selectively looping the early-middle transformer layers significantly improves both training efficiency and model performance in MDMs. We call this approach \textbf{LoopMDM} (Looped Masked Diffusion Model), which brings two key benefits: looping layers at training-time yields a depth-scaling effect without adding parameters, while varying the number of loops at inference-time enables flexible compute scaling. Despite the simplicity, the results are striking: across multiple pre-training corpora, LoopMDM matches the performance of same-size MDMs with up to $3.3\times$ fewer training FLOPs, while its final performance outperforms them on various reasoning benchmarks, including up to $+8.5$ points on GSM8K. It even surpasses deeper non-looped MDMs trained with comparable per-step compute, indicating that selective looping is more effective than naive depth scaling. Furthermore, LoopMDM can scale inference-time compute by increasing the number of loops. Adaptively adjusting the number of loops throughout the sampling process further yields additional gains in compute efficiency while maintaining performance. Lastly, with attention analysis, we provide evidence that looping is effective in MDMs by promoting interactions among masked positions. Our code and weights will be publicly released.

Understanding the internal routing of visual concepts is crucial for the safe and controllable adaptation of generative models. While concept localization has been widely studied in diffusion models, the emerging paradigm of next-scale visual autoregressive models remains largely unexplored. In this paper, we introduce LoCo, the first model-agnostic framework to localize where and when specific concepts emerge within autoregressive models. Driven by the native coarse-to-fine nature of next-scale generation, our method precisely maps conceptual knowledge across three distinct dimensions: Layer, Scale, and Position. To systematically localize and evaluate concept routing without context bias, we propose LoCoBench, a comprehensive dataset spanning 10 diverse categories. Extensive probing on image and video autoregressive models like Infinity, HunyuanImage-3.0, and InfinityStar shows that the localized positions are both interpretable and causally related to concept emergence. Building on these insights, we apply our localization method to three key applications: concept erasure, model personalization, and adversarial concept injection. Experiments demonstrate that our targeted intervention achieves state-of-the-art performance, substantially reducing computational overhead while preserving benign utility. Overall, our findings offer insights into how conceptual knowledge is routed during autoregressive generation, introducing a practical pathway for more interpretable, efficient, and secure adaptation.

Designing regulatory DNA sequences for targeted gene-expression control is an important challenge. Recent approaches frame this task as property-conditioned generation, where diffusion models trained on natural sequences are guided toward high predicted activity through reward-based fine-tuning or sampling-time guidance. We show that single-reward evaluation can obscure reward-hacking behavior. By decomposing evaluation into property, novelty, and plausibility, we identify an empirically underexplored region of the evaluation space in which all three objectives are satisfied, but no existing baseline succeeds. {We postulate that this gap arises because prior methods treat guidance primarily as a matter of magnitude.} In regulatory DNA, however, sequence grammar is spatially nonuniform: motif positions are sensitive to perturbation, while background regions allow more exploration. We therefore propose \textsc{LocoGen} by reformulate guidance as a problem of \textbf{locality}. \textsc{LocoGen} learns an invariant motif mask through sequence-level invariance learning to protect motif positions, while applying OOD damping only to background positions. It operates at sampling time on a frozen diffusion backbone, with no retraining. Across HepG2, K562, and SK-N-SH, \textsc{LocoGen} reaches this previously underexplored region of the property--novelty--plausibility space. Code is available at \url{https://huggingface.co/AnonymousAuthor42/LocoGen}.

Diffusion models are prone to generating structural hallucinations - samples that match the statistical properties of the training data yet defy underlying structural rules, resulting in anomalies like hands with more than five fingers. Recent research studied this failure mode from several viewpoints, offering partial explanations to their occurrence, such as mode interpolation. In this work, we propose a complementary perspective that treats hallucinations as instabilities on the model-induced manifold. We begin by showing that a hallucination filter based on such instabilities matches or exceeds the performance of the recently proposed temporal one. By tracing the source of these instabilities, we identify local intrinsic dimension (LID) as their primary driver and propose Intrinsic Quenching (IQ), a direct corrective mechanism that deflates it to alleviate hallucinations. IQ consistently outperforms standard hallucination reduction baselines across a wide array of benchmarks and offers a highly promising solution for enforcing anatomical consistency in downstream medical imaging tasks.

Low-Rank Adaptation (LoRA) has become a widely adopted technique in text-to-image diffusion models, enabling the personalisation of visual concepts such as characters, styles, and objects. However, existing approaches struggle to effectively compose multiple LoRA adapters, particularly in open-ended settings where the number and nature of required skills are not known in advance. In this work, we present LoRAtorio, a novel train-free framework for multi-LoRA composition that gates each adapter using only signals already inside the denoiser, specifically, patch-level cosine (dis)similarity between each LoRA's predicted noise and the base model's. We refer to this as ``intrinsic'' guidance because no external parameters are introduced. Our method is motivated by two key observations: (1) LoRA adapters trained on narrow domains produce unconditioned denoised outputs that diverge from the base model, and (2) when conditioned out of distribution, LoRA outputs show behaviour closer to the base model than when conditioned in distribution. These patch-level similarities are used to construct a spatially-aware weight matrix, which guides a weighted aggregation of LoRA outputs. To address domain drift, we further propose a modification to classifier-free guidance that incorporates the base model's unconditional score into the composition. We extend this formulation to a dynamic module selection setting, enabling inference-time selection of relevant LoRA adapters from a large pool. On the ComposLoRA benchmark, LoRAtorio achieves state-of-the-art performance, with a CLIPScore that does not deteriorate as the number of composed adapters grows, surpassing the strongest prior method by up to 1.3% in CLIPScore, and reaching a 76.92% GPT-4V win rate against the closest baseline. We further show that the framework is backbone-agnostic: the intrinsic-similarity principle transfers to rectified-flow architectures (FLUX.1-dev) without retraining. Code will be made available.

Interactive streaming music generation promises the use of generative models for live performance and co-creation that is impossible with offline models. However, SOTA models exist in the discrete-AR regime, requiring industrial levels of compute for both training and inference. In this work, we investigate whether audio diffusion models, with their wide support in the open-source community but non-streaming bidirectional nature, can be repurposed efficiently into interactive models accessible on consumer hardware. By taking a critical look at the modern pipeline for block-wise outpainting diffusion, we identify critical inefficiencies during inference that result in strictly worse computational efficiency than their discrete-AR counterparts. We propose Live Music Diffusion Models (LMDMs), a simple modification of the generative diffusion process that recovers, and then outperforms, the inference complexity of the discrete Live Music Models (LMMs) through block-wise KV Caching. Unlike LMMs, LMDMs further enable stable post-training alignment through our novel ARC-Forcing paradigm, reducing error accumulation without any explicit RL or reward models. We demonstrate the application of LMDMs in a number of creative domains, including text-conditioned generation, sketch-based music synthesis, and jamming. We finally show how LMDMs can be used as a generative instrument in a real artist-AI collaboration, utilizing LMDMs as a “generative delay” to transform musicians’ improvisation live for variable timbral effects while running locally on a consumer gaming laptop.

Score-based valuation methods, such as Shapley values and Leave-one-out (LOO), are widely used to assign value to data in modern machine learning pipelines, including for tasks such as attribution, selection, and pricing, yet it remains unclear when these scalar scores reliably guide downstream decisions. We show that their success is governed by three structural properties of the learning problem: substitutability, complementarity, and non-monotonicity. Substitutability (redundancy) can collapse pointwise credit, causing Shapley and LOO to fail even under monotone submodular valuations; bounded curvature limits this collapse and helps recover constant-factor approximation. Complementarity can break common score-based rules and greedy-style adaptive selection, though these effects diminish with sufficient coverage. Non-monotonicity implies that all non-adaptive methods, including score-based approaches, can fail, establishing a separation from adaptive algorithms. Our theoretical results, supported by empirical evidence, provide a structural view of data valuation and motivate a simple practical pipeline: deduplicate to reduce redundancy, ensure coverage to suppress complementarity, and then choose between score-based or adaptive methods based on non-monotonic effects.

Localizing AI-edited regions is essential for interpretable forensic analysis, but remains challenging due to subtle and spatially distributed artifacts that are misaligned with semantic or object boundaries. Existing approaches rely on pixel-level supervision from controlled editing pipelines, which is difficult to scale and can introduce misleading signals: artifacts frequently extend beyond annotated regions, while out-of-mask pixels are treated as authentic. This limits models' ability to capture transferable evidence and generalize across generators and datasets. To address these issues, we propose \textbf{ReGFLoW}, a \textbf{Re}construction-\textbf{G}uided \textbf{F}ake \textbf{Lo}calization framework under \textbf{W}eak supervision, which is the first weakly supervised approach for diffusion-edited fake region localization. ReGFLoW requires only real/fake labels at the image-level and uses diffusion reconstruction errors as dense spatial guidance to inject them into both feature and score spaces. Furthermore, by artifact-centric multiple instance learning, ReGFLoW utilizes localized diffusion evidence without relying on semantic-affinity or boundary-based pseudo-mask priors. Extensive experiments demonstrate that ReGFLoW achieves stronger out-of-domain generalization than fully supervised learning baselines.

Diffusion and flow generative models sample by integrating a learned ODE, but high quality still requires many sequential model evaluations. Solver learning reduces this cost by adapting scalar coefficients, timesteps, or both, while keeping the backbone model fixed. In this work, we identify a structural bottleneck in this update family: each step remains span-limited. Each update remains a scalar-weighted combination of buffered velocity evaluations, so learning can reduce the in-span teacher mismatch but cannot represent the out-of-span residual exposed by large steps. We propose SpanLift, a lightweight operator-augmented neural solver that enlarges the update family beyond scalar-coefficient solvers. SpanLift keeps a fixed base solver as an in-span prior and learns a spatial residual operator over the state and velocity buffer. The operator is trained by endpoint teacher matching, preserves the pretrained backbone, and adds no model NFEs. Empirically, the learned correction transfers across base solvers and is predominantly out-of-span. Across pixel-space diffusion, latent flow matching, and precipitation nowcasting, SpanLift achieves state-of-the-art few-step sampling. With only 3 NFE, it improves CIFAR-10 FID from 8.16 to 5.69 and ImageNet FID from 17.37 to 11.83.

Visual textures, defined as spatially homogeneous image regions containing repeated elements (e.g. a field of grass, the bark of a tree), are ubiquitous in visual scenes and provide important cues for recognizing materials and objects. Existing texture models extract essential statistics from a single texture image, and can then generate high-quality samples that are visually similar to the original by matching these statistics. However, their statistics are either hand-designed or based on a network pretrained for another purpose (e.g., object recognition). Here, we develop the first principled method for unsupervised learning of a set of statistics that are used to constrain a maximum entropy probability model. We leverage methods developed for generative diffusion models to derive training and sampling procedures, and compare these to the traditional method of sampling via matching the statistics. Despite the compactness of our trained model (512 statistics), it generates texture images whose quality is as good or better than the current state-of-the-art model (~177k statistics). A more direct comparison of the two models, obtained by synthesizing images that are indistinguishable for one model but maximally different for the other, reveals their relative strengths and weaknesses. Finally, we show that, unlike previous statistical texture models, a straight trajectory in the representation space of our model generates homogeneous texture samples that interpolate smoothly between the features of the two end points.

Recent latent diffusion methods jointly model multiple representations of an image, denoising them with asynchronous noise schedules in which one representation temporally leads another. However, existing asynchronous schedules are often hand-designed, relying on grid search over simple function classes. We propose to learn the asynchronous schedule directly. We parameterize the schedule as a convex monotone bijection $f : [0,1] \to [0,1]$, where convexity together with $f(0)=0$ and $f(1)=1$ guarantees the desired leading-representation property by construction while still admitting a wide family of schedule shapes. A short probe stage jointly optimizes the schedule and diffusion model under a mild speed regularizer; the resulting smooth schedule is averaged over the stable probe window, frozen, and reused for full training, introducing no additional overhead during the main training stage. On ImageNet 256$\times$256, our learned schedule reaches unguided FID 2.37 at 1M iterations and FID 1.05 with AutoGuidance at 200 epochs, outperforming the best hand-tuned baseline trained for four times longer. Code is available at \url{https://anonymous.4open.science/r/LAS_public-01E4/}.

World models predict future transitions from observations and actions. Existing works predominantly focus on image generation only. Visual feature-based world models, on the other hand, predict future visual features instead of raw video pixels, offering a promising alternative that is more efficient and less prone to hallucination. However, current feature-based approaches rely on direct regression, which leads to blurry or collapsed predictions in complex interactions, while generative modeling in high-dimensional feature spaces still remains challenging. In this work, we discover that a new type of latent action representation, which we refer to as *Residual Latent Action* (RLA), can be easily learned from DINO residuals. We also show that RLA is predictive, generalizable, and encodes temporal progression. Building on RLA, we propose *RLA World Model* (RLA-WM), which predicts RLA values via flow matching. RLA-WM outperforms both state-of-the-art feature-based and video-diffusion world models on simulation and real-world datasets, while being orders of magnitude faster than video diffusion. Furthermore, we develop two robot learning techniques that use RLA-WM to improve policy learning. The first one is a minimalist world action model with RLA that learns from actionless demonstration videos. The second one is the first visual RL framework trained entirely inside a world model learned from offline videos only, using a video-aligned reward and no online interactions or handcrafted rewards.

Learning permutations is fundamental to sorting, ranking, and matching, but existing differentiable methods based on entropy-regularized Sinkhorn produce a single softened solution and collapse under ambiguity. We present PermFlow, a conditional flow matching framework that operates directly on the affine subspace of matrices with unit row and column sums. A closed-form tangent-space projector preserves these constraints exactly along every trajectory, by construction rather than through iterative correction, and a nearest-target coupling routes distinct noisy initializations toward distinct valid permutations. The result is a model that captures multimodal permutation distributions rather than collapsing them to a single mode. On a visual sorting task with blended-digit ambiguity and a symmetric linear assignment problem, PermFlow achieves high accuracy on unambiguous inputs and recovers both valid permutations under ambiguity, where Sinkhorn-based baselines structurally fail.

Neural network verification is key to certifying robustness in safety-critical systems. Sound verifiers commit to abstract domains that propagate soundly through the network's operations, paying for that commitment with looseness at scale and applicability largely confined to piecewise-linear architectures. Probabilistic verifiers relax soundness, but they too commit to a fixed family of shapes for the network's reachable outputs. When the network's true output geometry differs from the chosen shape, the verifier over-approximates the reach-set and fails to certify networks that are in fact safe. We propose instead to learn the reach-set geometry from the network's behavior. A flow-matching model trained on input-output samples and calibrated by conformal prediction yields a probabilistic reach set whose shape adapts to the true shape of the reach-set rather than to an a priori choice. The resulting set has no closed-form description, so we reframe the specification check as a rare-event estimation problem on the learned distribution, restricted to the calibration's coverage region, and solve it with bounded adaptive multilevel splitting. The pipeline produces a probabilistic safety certificate combining the conformal coverage with a rare-event upper bound. Our pipeline performs comparably to sound verifiers on a subset of VNN-COMP 2025 benchmarks where sound verification is tractable and matches or exceeds fixed-shape probabilistic baselines on most benchmarks in the same suite. On a synthetic family of growing-depth networks, it scales sub-exponentially where sound verifiers time out or abstain.