NeurIPS 2026 论文列表

Flow matching has recently emerged as a strong paradigm for state-of-the-art text-to-image (T2I) generation, enabling high-quality generation with a small number of sampling steps. As these models are increasingly integrated into real-world applications, ensuring safe and non-sensitive content generation has become a critical requirement. However, adapting safety and concept removal methods to this new generation framework remains an open challenge. Specifically, prior methods largely rely on iterative trajectory steering across a number of denoising steps or on CLIP-centeric prompt embedding manipulation. These design assumptions pose fundamental bottlenecks for safety in flow matching-based T2I generation, where limited sampling steps constrain iterative correction and modern context-aware text encoders diminish the effectiveness of embedding-level interventions. In this paper, we propose VESFlow, a training-free safety method tailored to flow matching with extremely few sampling steps. Leveraging the fact that flow matching models learn the marginal velocity (or average velocity in MeanFlow), we directly edit the velocity field via a Bayesian decomposition of the safe-conditional posterior. VESFlow steers the trajectory toward safe outputs while leaving the conditioning prompt unchanged. Building on the observation that VESFlow leaves outputs unchanged under benign prompts, we further introduce a risk score filtering that bypasses velocity editing to reduce computational cost while preserving benign prompt generation. Based on this filtering, we proposed VESFlow+ which provides stronger safety protection when filtered by the risk score. Experimental results show that our method removes the target concept, reducing the detection rate by NudeNet to 6.3\% for step-4 model, while preserving fidelity on benign prompts. Code is available at the supplementary file.

Logical reasoning remains a major challenge for large language models (LLMs), particularly on structured problems that require precise constraint tracking, consistency preservation, and multi-step deduction. This challenge is especially acute for small-scale LLMs, which are more prone to producing inconsistent, redundant, or brittle reasoning trajectories. Existing approaches for improving logical reasoning largely optimize for final-answer correctness, providing only weak supervision over the intermediate reasoning process. In this work, we propose SPRING, a solver-guided reinforcement learning framework for logical reasoning that uses an SMT solver as a training-time verifier of intermediate reasoning steps to provide process-level supervision. SPRING introduces the notion of a novel reasoning step, namely, a step that is logically valid, consistent with the evolving reasoning state, and not already implied by previously accepted non-contradictory deductions. Based on this solver-based assessment, we design process rewards that encourage novel inferential progress while penalizing contradictory and uninformative reasoning steps. Evaluation results on two logical reasoning benchmarks, ZebraLogic and AR-LSAT, show that SPRING consistently outperforms baseline LLMs and outcome-only reward baselines. On ZebraLogic, SPRING improves puzzle accuracy by up to 49.71 and 15.43 points over the base LLM and outcome-only reward baseline, respectively. On AR-LSAT, SPRING improves the overall average score by up to 64.93 and 12.14 points over the base LLM and best-performing outcome-only reward baseline, respectively.

We introduce SNACK, a string representation for probabilistic graph generation that enables sequence models to generate and model graph-structured data. SNACK linearizes graphs by encoding the nonzero entries of the lower-triangular adjacency matrix, establishing a bijective correspondence between valid sequences and ordered adjacency matrices. This design supports invalid logit masking for enforcing structural constraints, including chemical valence and ordering constraints, and enables principled string-based GFlowNet training by explicitly accounting for node-ordering symmetries. Across standard graph-generation tasks and molecular distribution-learning benchmarks, SNACK achieves competitive or state-of-the-art sample quality, while substantially improving the throughput of GFlowNet training relative to graph-based generation. Probing analyses further show that models trained on SNACK encode meaningful local and global graph structure despite receiving only sequential supervision. These results position SNACK as a practical framework for probabilistic graph generation with deep sequence models.

High-resolution 3D generation increasingly relies on voxel latents and multi-stage pipelines that first predict active structure and then synthesize local geometry. While effective, this design fragments continuous surfaces into many local tokens, inflates generation cost, and often weakens topological consistency for thin or highly connected shapes. We introduce **SILSA**, a topology-aware 3D generation framework that represents shapes with compact sliding-window slice latents. Instead of generating expensive voxel tokens, SILSA uses a fixed set of overlapping slices along the three canonical axes, where each token summarizes a local depth window to preserve cross-sectional continuity and support single-stage rectified-flow generation. A **Slice VAE** encodes oriented surface samples into multi-axis slice latents and reconstructs them with a sparse volumetric decoder, while a **Volumetric Anchor Lattice** coordinates directional slice streams through a shared 3D workspace. To preserve structural correctness, we introduce slice-level topology supervision that matches persistence diagrams and aligns Betti transitions across neighboring slices. Experiments show that SILSA improves structural fidelity while substantially reducing generation cost. SILSA improves PSNR by 8.7%, coverage by 5.96 absolute points, and Betti error by 9.2% over the strongest baseline, while using 70.0% fewer tokens than the next-most compact baseline and over 98% fewer tokens than sparse or hierarchical tokenizers, reducing training memory by 40.4% and inference time by 58.5%. Qualitative results further show improved preservation of thin structures, repeated components, and long-range connectivity.

Text-driven image editing has advanced rapidly, but reliably localizing these manipulations requires image manipulation localization (IML) models trained on large pixel-annotated datasets, and there is still no low-cost way to obtain such training data at scale. We observe that these data already exist in disguise: public editing datasets contain millions of structurally identical $\textit{(original, edited)}$ pairs to IML training samples, lacking only pixel-level masks. Recovering these masks automatically is non-trivial: pixel differencing is overwhelmed by diffusion-induced perturbations across all pixels, and instruction-only grounding localizes only what the prompt describes, missing unintended editor side-effects. We propose $\textbf{SIGMA}$ ($\textbf{S}$emantic-difference $\textbf{I}$nstruction-$\textbf{G}$rounding $\textbf{M}$ask $\textbf{A}$nnotator), which performs semantic-feature differencing in a vision foundation backbone and injects an instruction-derived spatial prior into this visual stream via bidirectional cross-modal refinement, amplifying the difference signal at intended-edit regions when the editor faithfully realizes user intent. SIGMA is trained in two complementary stages: Stage I supervises on inpainting masks; Stage II closes the diffusion-domain shift via VAE-roundtrip noise calibration, EMA self-training, and an edit-noise disentanglement loss. SIGMA outperforms existing automatic mask generators on five benchmarks ($\textbf{+12.20\%}$ F1, $\textbf{+11.16\%}$ IoU). When applied to public editing corpora, it produces a $\sim$1.1M IML training set that improves six diverse detectors by $\textbf{+18.34\%}$ F1 across five datasets, turning previously unused editing data into a model-agnostic supervisory resource for IML. For reproducibility, our anonymized code is available at https://anonymous.4open.science/r/SIGMA-14FE.

Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resolutions beyond their training range. Existing training-free approaches mitigate this by modifying inference-time attention behavior, often through Rotary Position Embeddings (RoPE) extrapolation combined with attention scaling. However, these strategies apply a uniform and content-agnostic scaling across RoPE components with distinct frequency characteristics, inducing a trade-off between preserving global structure and recovering fine detail. We introduce \textbf{SEGA}, a training-free method that dynamically scales attention across RoPE components according to the latent’s spatial-frequency structure at each denoising step. This adaptive scaling improves both structural coherence and fine-detail fidelity. Experiments show that SEGA consistently improves high-resolution synthesis across multiple target resolutions, outperforming state-of-the-art training-free baselines.

We propose SCULPT, a state-of-the Art masked discrete diffusion model (MDMs) for high resolution text-to-image synthesis. Compared with prior works on masked image generation, SCULPT addresses two key challenges. First, unlike continuously diffusion models which progressively refines image latent across the entire image, vanilla MDMs do not have self-correcting capability because discrete tokens cannot be changed once it's unmasked. Second, while scaling the vocabulary size of discrete image tokenizers can improve reconstruction quality, it also introduces optimization challenges for training generative models as per-token training signal becomes more spares. To address the first challenge, SCULPT incroprates a token-editing mechanism where the model can dynamically correct already-unmasked output tokens during inference. To address the second challenge. we proposed a Goruped Corss Entrophy (GCE) objective that assigns positive learning signal to adjacent tokens of the ground truth in the embedding space. To improve the training efficiency, we further implemented a custom fused operator that greatly reduce the VRAM requirements during training in large-vocabulary setting. Experiment results show that these innovations significant improves the training efficiency and image fidelity of masked discrete image generators.

AI-generated image detection has become an important problem in media forensics as modern generative models produce increasingly realistic images. Recent CLIP-based detectors show strong generalization ability, but CLIP image features entangle semantic content with forensic cues. Since semantic content is not an intrinsic generation trace, relying on it can introduce semantic shortcuts and unstable performance under unseen generator shifts. In this paper, we propose SAGE, a Semantic-Agnostic Image Embedding framework for generalized AI-generated image detection. SAGE constructs paired triplets of COCO images, SDXL-reconstructed images, and COCO captions so that real and fake images share the same caption-level semantics. It then suppresses semantic information by suppressing the semantic direction provided by CLIP text embeddings from CLIP image embeddings. To enable caption-free inference, SAGE learns a semantic anchor that approximates the role of paired text embeddings at test time. In addition, SAGE adopts a SoftTriple-style sub-center classifier to model intra-class variation in real and fake images, yielding a more stable authentication geometry across diverse generators. Experiments on CommunityForensics demonstrate that SAGE achieves competitive detection performance while substantially reducing generator-wise performance variation. Further analyses show that SAGE effectively reduces semantic dependence and forms a clearer real/fake feature geometry than strong baselines.

Detecting text generated by large language models (LLMs) is a critical line of defense for ensuring information content security. Although recent studies have gradually shifted to evaluating the robustness of detectors, existing benchmarks generally suffer from two primary limitations: (1) they lack granularity in controlling perturbation intensity, making it difficult to systematically evaluate the dynamic changes in detector performance as attack intensity increases; and (2) they fail to investigate the impact of perturbation intensity on detector robustness within complex scenarios, such as cross-domain and cross-model settings. To address these challenges, we propose \textbf{RobustStress}, a novel stress-testing framework for intensity-controlled perturbations. We achieve quantitative classification of perturbation intensity by varying the proportion of synonym replacement and employing graded LLM-based paraphrasing attacks. Experiments reveal distinct patterns of performance degradation as perturbation intensity increases, and further capture the synergistic weakening effect between cross-scenario shifts and adversarial perturbations. RobustStress provides an effective stress-testing framework for evaluating detectors in real-world scenarios, encouraging the community to move beyond performance on clean benchmarks to the development of more robust defense mechanisms against adversarial attacks.

Moving an object in a single image requires geometry-consistent spatial rearrangement, including handling occlusions, revealing previously unseen regions, and maintaining coherent shadows and reflections. Existing approaches are not well suited to this setting and often fail to preserve such scene-level consistency. We address this problem by introducing a geometry-aware object motion method that operates directly on the internal representations of diffusion transformers. Our key insight is that rotary positional embeddings (RoPE) define a structured spatial field that can be explicitly manipulated to induce controlled motion. We extend 2D RoPE into a depth-aware formulation that encodes 3D spatial structure, enabling consistent object displacement and scene-aware updates. Our model is trained using synthetic data combined with a small set of real images via parameter-efficient fine-tuning. Despite minimal real supervision, it preserves object identity under large spatial displacements, generates plausible content in newly revealed regions, and consistently updates scene-dependent effects such as shadows and illumination. Experimental results demonstrate the superiority of our method.

As AI-assisted image editing becomes increasingly prevalent, Text-Centric Image Forgery Localization (TFL) is essential for protecting trust in financial and legal records. However, we observe that existing TFL detectors predominantly rely on Full-Parameter Fine-Tuning (FPFT) and fail to generalize to unseen forgery types because FPFT can induce low-rank feature collapse and overfit training artifacts. Meanwhile, prior detectors capture diverse forgery traces with a single unified representation, making subtle traces entangled and difficult to learn. To address these challenges, we propose RiSE, a Residual Subspace Expert model that preserves pre-trained priors by freezing principal SVD components and adapting only the residual subspaces with a ViT-only segmentor to avoid feature collapse. RiSE introduces forgery-aware residual experts, where each expert is trained independently on a training subset with a particular forgery type, and we show that cross-domain localization performance improves consistently as more experts are added. At inference, we introduce Latent Perturbation Confidence (LPC), which selects the most confident expert by analytically computing the latent-perturbed output. LPC enables efficient confidence estimation with a single forward pass, avoiding repeated forward passes on perturbed samples and improving expert selection. By training on synthetic forgery data, RiSE with 1 expert outperforms state-of-the-art methods on real-world forgery images by 20.4\% while reducing training steps by $10\times$. Scaling the number of experts to 9 yields a 35.8\% gain. RiSE also remains effective with DCT feature fusion, even when the majority of the parameters is frozen with RGB-only pretraining. The code is in the supplementary material.

Language model query generation is the task of using a language model to translate a natural-language request into a formal query, which is then executed to retrieve information from databases or knowledge graphs. Recent approaches rely on reinforcement learning (RL) to enhance the model’s reasoning and improve query correctness. However, existing methods provide only sequence-level rewards, resulting in sparse feedback that is difficult to optimize. To address this limitation, we propose a reward shaping method that learns a token-level, and thus dense, reward function, providing fine-grained supervision to guide the language model toward correct queries. We formulate this problem as a bilevel optimization problem where the upper level learns a token-level shaping reward from ground truth sequence-level reward and the lower level optimizes the language model using the learned shaping reward. We propose a single-loop algorithm to solve this problem and theoretically guarantee that the algorithm converges at $O(\frac{1}{\sqrt{K}})+O(\frac{\log K}{\sqrt{K}})$. Extensive experiments demonstrate that our method outperforms the baselines.

We present a robust deep clustering framework for unsupervised visual discovery that bridges the gap between statistical robustness and mathematical tractability. Current generative approaches typically rely on either noise-prone Gaussian priors or computationally intensive diffusion models; however, neither paradigm simultaneously offers explicit latent structures and exact analytic optimization. While diffusion models generate strong priors, their reliance on iterative sampling and intractable likelihoods limits their scalability and interpretability in clustering tasks. Our approach addresses these limitations by constructing a latent space governed by a Student's $t$ distribution via a Bayesian scale-mixture formulation. This yields the first fully closed-form augmented evidence lower bound (ELBO) for this model class, effectively eliminating the biased variational approximations and high computational costs inherent in prior heavy-tailed or diffusion-based frameworks. By treating precision as a latent variable, our objective automatically modulates the influence of each data point; it downweights outliers to learn a data-dependent measure of trust. This mechanism leads to superior robustness and more stable manifold learning compared to state-of-the-art approaches. We demonstrate the resilience of our framework on standard vision benchmarks and complex neuroimaging tasks. In real-world brain magnetic resonance imaging (MRI)-driven neurodegenerative disease analysis, our model successfully recovers clean and anatomically coherent clusters where clinical noise typically collapses rare subtypes. These results underscore the ability of our framework to preserve clinically crucial morphological subtypes, allowing precise discovery within clinical interventions.

Maintaining long-term geometric consistency remains a key challenge in long-horizon autoregressive video generation. Recent memory-augmented generative models address this issue by retrieving historical frames beyond the limited temporal context, but their effectiveness depends on two key design choices: what 3D-geometric evidence should represent past observations, and how memory frames should be selected from this evidence. Existing methods often rely on camera poses or field-of-view overlap, which are lightweight but too coarse to reason about pixel-wise visibility, or use explicit 3D reconstruction, which provides fine-grained evidence but is costly to maintain over long rollouts. We propose Coverage-Maximizing Retrieval-Augmented Generation (COVRAG), a depth-based memory retrieval framework that uses pretrained 3D priors to construct a target-view coverage map as lightweight 3D memory evidence. For frame selection, COVRAG maximizes residual coverage gain, iteratively retrieving frames that explain target-view regions not covered by the current context or previously selected memories. To improve scalability in long-video generation, we introduce a sliding-window depth caching for efficient geometry estimation. Experiments on RealEstate10K and DL3DV show that \modelname improves long-horizon geometric consistency while maintaining low latency compared to baselines.

CLIP-style contrastive image--text pretraining is widely used in radiology data, where each image is paired with one report and every other report in the batch is treated as a negative. Under this recipe, two failures appear, neither systematically addressed by existing contrastive learning theory: zero-shot evaluation peaks then degrades while training loss keeps decreasing, and training fails to learn at all at large batches. We hypothesize the cause is structural rather than radiology-specific: many unpaired reports share clinical findings with a given image, so CLIP's paired-identity target is systematically biased, not merely noisy. To test this, we construct CLEVR-Radiology, a synthetic testbed that preserves only this overlapping-fact structure and reproduces both failures. With evidence that the structure is sufficient to reproduce the failures, we develop a target-misspecification theory that derives both failures from a single deterministic gradient bias amplified by batch size, and use it to motivate a minimal compatibility-based correction, CorLIP: a text is treated as positive whenever its clinical assertions agree with the image, with no other change to the training pipeline. Beyond benchmark improvements, CorLIP removes the post-peak degradation, makes large-batch training succeed where it previously collapsed, substantially amplifies the gains from more data, and is the only configuration that remains stable up to B=2048. The correction also transfers from chest X-ray to 3D CT modalities.

Standard training of diffusion models typically relies on a forward diffusion process anchored by ground-truth target images. However, in image fusion tasks, the scarcity of real fused images makes it difficult to formulate a forward process, thereby precluding the standard training. Fortunately, our visual analysis reveals that image fusion can be effectively modeled without standard training or reliance on the real images. Nevertheless, the misalignment of input image pairs remains a significant bottleneck for fusion quality. Recognizing that one-off registration is ill-suited to the progressive generation of diffusion models, we propose a unified registration-fusion framework driven by a time-aware joint optimization mechanism. Specifically, we design a time-aware registration network to progressively optimize registration to guide fusion, while the fusion results provide feedback constraints to the registration network at each time step. This mechanism facilitates joint optimization of registration and fusion, significantly improving the quality of fused results. Experimental results show that the proposed method performs excellently on multiple datasets, validating its effectiveness and superiority.

We show that Fréchet Distance (FD), long considered impractical as a training objective, can in fact be effectively optimized in the representation space. Our idea is simple: decouple the population size for FD estimation (e.g., 50k) from the batch size for gradient computation (e.g., 1024). We term this approach FD-Loss. Optimizing FD-Loss reveals several surprising findings. First, post-training a base generator with FD-Loss in different representation spaces consistently improves visual quality. Under the Inception feature space, a one-step generator achieves 0.72 FID on ImageNet $256\times256$. Second, the same FD-Loss repurposes multi-step generators into strong one-step generators without teacher distillation, adversarial training or per-sample targets. Third, FID can misrank visual quality: modern representations can yield better samples despite worse Inception FID. This motivates FDr$^{k}$, a multi-representation metric. We hope this work will encourage further exploration of distributional distances in diverse representation spaces as both training objectives and evaluation metrics for generative models. Code and checkpoints will be open-sourced.

Existing MLLM-based UI-to-Code generation methods can generate complete HTML/CSS codes through end-to-end or multi-stage pipelines, yet the generated codes often contain structural errors such as incorrect repeated layouts, wrong component boundaries, or missing interaction slots. Subsequent generations may continue along the erroneous structure, causing the error to propagate and amplify. This paper studies post-generation repair: how can we locate and repair unreliable local DOM structures? We observe that this repair process is ambiguous in two ways: a mismatch between the target screenshot and the output may correspond to multiple plausible DOM subtrees, and a single DOM subtree may admit multiple repairs with different rendered behaviors. We propose Render Structure Uncertainty (RSU)for partial DOM repair, a browser grounded uncertainty layer that can be attached to any base HTML generator. RSU parses the target screenshot into a visual structure graph and converts the browser execution trace of the generated code into a DOM-anchored render structure graph. By matching these graphs, RSU yields structural mismatches and a small set of candidate DOM holes, preserving error attribution uncertainty. For each hole, RSU generates multiple local candidates, renders them in the full page context, and clusters them using render-structure signatures that encode layout relations, repeated patterns, content slots, semantic roles, and invalid states, thereby modeling repair uncertainty. The retained representative candidates form a compact Partial DOM candidate set, over which we perform global reranking to produce the final HTML code. In this way, RSU reframes HTML repair into uncertainty-guided search in render-structure space, avoiding premature commitment to either a single error location or a single local repair. Experiments show that RSU improves the generation quality of base models, producing higher-quality HTML with better layout consistency and fewer local structural errors.

The success of deep learning in medical image analysis is often hindered by the long-tail distribution of disease cases, where rare or early-stage tumors are critically under-represented. While controllable synthesis offers a potential solution, existing methods suffer from a \textit{specification bottleneck}, as low-dimensional signals like text or binary masks fail to capture complex textures and morphological variations. In this paper, we propose an exemplar-driven synthesis framework that utilizes real tumor samples as high-dimensional templates to enable precise, case-specific generation. To the best of our knowledge, this is the first work to introduce reinforcement learning (RL) into the field of 3D medical image generation, called **MedGRPO**. We formulate the unpaired tumor synthesis task as a constrained trajectory optimization problem and leverage Flow-GRPO to find an optimal generation path. By designing a multi-objective reward system encompassing texture, shape, and semantic consistency, our model effectively balances pathological fidelity with anatomical coherence without requiring paired supervision. Rigorous evaluations across four major tumor types and the external AbdomenAtlas 2.0 dataset demonstrate that our method produces high-fidelity synthetic data that significantly enhances the performance of downstream diagnostic models.