ICLR 2026 论文列表

All-in-one image restoration (IR) aims to recover high-quality images from diverse degradations, which in real-world settings are often mixed and unknown. Unlike single-task IR, this problem requires a model to approximate a family of heterogeneous inverse functions, making it fundamentally more challenging and practically important. Although recent focus has shifted toward large multimodal models, their robustness still depends on faithful low-level inputs, and the principles that govern effective restoration remain underexplored. We revisit attention mechanisms through the lens of all-in-one IR and identify two overlooked bottlenecks in widely adopted Restormer-style backbones: \textit{(i) the value path remains purely linear}, restricting outputs to the span of inputs and weakening expressivity, and \textit{(ii) the absence of an explicit global slot} prevents attention from encoding degradation context. To address these issues, we propose two minimal, backbone-agnostic primitives: a nonlinear value transform that upgrades attention from a selector to a selector–transformer, and a global spatial token that provides an explicit degradation-aware slot. Together, these additions improve restoration across synthetic, mixed, underwater, and medical benchmarks, with negligible overhead and consistent performance gains. Analyses with foundation model embeddings, spectral statistics, and separability measures further clarify their roles, positioning our study as a step toward rethinking attention primitives for robust all-in-one IR.

Recently, instruction-based image editing (IIE) has received widespread attention. In practice, IIE often modifies only specific regions of an image, while the remaining areas largely remain unchanged. Although these two types of regions differ significantly in generation difficulty and computational redundancy, existing IIE models do not account for this distinction, instead applying a uniform generation process across the entire image. This motivates us to propose \textbf{RegionE}, an adaptive, region-aware generation framework that accelerates IIE tasks without additional training. Specifically, the RegionE framework consists of three main components: 1) Adaptive Region Partition. We observed that the trajectory of unedited regions is straight, allowing for multi-step denoised predictions to be inferred in a single step. Therefore, in the early denoising stages, we partition the image into edited and unedited regions based on the difference between the final estimated result and the reference image. 2) Region-Aware Generation. After distinguishing the regions, we replace multi-step denoising with one-step prediction for unedited areas. For edited regions, the trajectory is curved, requiring local iterative denoising. To improve the efficiency and quality of local iterative generation, we propose the Region-Instruction KV Cache, which reduces computational cost while incorporating global information. 3) Adaptive Velocity Decay Cache. Observing that adjacent timesteps in edited regions exhibit strong velocity similarity, we further propose an adaptive velocity decay cache to accelerate the local denoising process. We applied RegionE to state-of-the-art IIE base models, including Step1X-Edit, FLUX.1 Kontext, and Qwen-Image-Edit. RegionE achieved acceleration factors of 2.57×, 2.41×, and 2.06×, respectively, with minimal quality loss (PSNR: 30.520–32.133). Evaluations by GPT-4o also confirmed that semantic and perceptual fidelity were well preserved. Code will be open-sourced.

Pixel-space generative models are often more difficult to train and generally underperform compared to their latent-space counterparts, leaving a persistent performance and efficiency gap. In this paper, we introduce a novel two-stage training framework that closes this gap for pixel-space diffusion and consistency models. In the first stage, we pre-train encoders to capture meaningful semantics from clean images while aligning them with points along the same deterministic sampling trajectory, which evolves points from the prior to the data distribution. In the second stage, we integrate the encoder with a randomly initialized decoder and fine-tune the complete model end-to-end for both diffusion and consistency models. Our framework achieves state-of-the-art empirical results on ImageNet. Specifically, our diffusion model reaches an FID of 1.58 on ImageNet-256 and 2.35 on ImageNet-512 with 75 number of function evaluations (NFE) surpassing prior pixel-space methods and VAE-based counterparts by a large margin in both generation quality and training efficiency. In a direct efficiency comparison, our model significantly outperforms DiT while using only around 30\% of its training compute. Furthermore, our one-step consistency model achieves an impressive FID of 8.82 on ImageNet-256, significantly outperforming its latent-space counterparts. To the best of our knowledge, this marks the first successful training of a consistency model directly on high-resolution images without relying on pre-trained VAEs or diffusion models.

With the rapid progress of large language models (LLMs), multimodal frameworks that unify understanding and generation have become promising, yet they face increasing complexity as the number of modalities and tasks grows. We observe that motion quantization introduces approximation errors that cap motion quality, and that unifying discrete text and continuous motion within a single-stream backbone amplifies cross-modal interference. Motivated by recent multi-branch Transformer designs that separate signals from different modalities, we propose MotionGPT3, a bimodal motion–language model for both understanding and generation. MotionGPT3 encodes raw motion into a continuous latent space using a variational autoencoder (VAE), thereby avoiding quantization-induced artifacts, while leveraging the semantic prior of pretrained language models. A dual-stream Transformer with shared attention preserves modality-specific routes while enabling controlled, bidirectional information flow, which reduces interference, stabilizing optimization, and empirically accelerates convergence without degrading fidelity. For multimodal joint training, a generate-then-align three-stage schedule further improves stability and limits cross-task interference. Experiments show that MotionGPT3 achieves 2× faster convergence in training loss and up to 4× faster convergence in validation, while maintaining state-of-the-art performance on standard motion understanding and motion generation benchmarks.

Despite recent progress in text-to-image (T2I) generation, existing models often struggle to faithfully capture user intentions from short and under-specified prompts. While prior work has attempted to enhance prompts using large language models (LLMs), these methods frequently generate stylistic or unrealistic content due to insufficient grounding in visual semantics and real-world composition. Inspired by recent advances in reasoning for language model, we propose RePrompt, a novel reprompting framework that introduces explicit reasoning into the prompt enhancement process via reinforcement learning. Instead of relying on handcrafted rules or stylistic rewrites, our method trains a language model to generate structured, self-reflective prompts by optimizing for image-level outcomes. The tailored reward models assesse the generated images in terms of human preference, semantic alignment, and visual composition, providing indirect supervision to refine prompt generation. Our approach enables end-to-end training without human-annotated data. Experiments on GenEval and T2I-Compbench show that RePrompt significantly boosts spatial layout fidelity and compositional generalization across diverse T2I backbones, establishing new state-of-the-art results. Code: https://github.com/microsoft/DKI_LLM/tree/main/RePrompt.

Multimodal representation learning models have demonstrated successful operation across complex tasks, and the integration of vision-language models (VLMs) has further enabled embedding models with instruction-following capabilities. However, existing embedding models lack visual-interactive capabilities to specify regions of interests from users (e.g., point, bounding box, mask), which have been explored in generative models to broaden their human-interactive applicability. Equipping embedding models with visual interactions not only would unlock new applications with localized grounding of user intent, which remains unexplored, but also enable the models to learn entity-level information within images to complement their global representations for conventional embedding tasks. In this paper, we propose a novel **V**isual-**I**nte**R**active **T**ext-Image **U**niversal **E**mbedder (**VIRTUE**) that extends the capabilities of the segmentation model and the vision-language model to the realm of representation learning. In VIRTUE, the segmentation model can process visual prompts that pinpoint specific regions within an image, thereby enabling the embedder to handle complex and ambiguous scenarios more precisely. To evaluate the visual-interaction ability of VIRTUE, we introduce a large-scale **S**egmentation-and-Scene **Ca**ption **R**etrieval (**SCaR**) benchmark comprising 1M samples that aims to retrieve the text caption by jointly considering the entity with a specific object and image scene. VIRTUE consistently achieves a state-of-the-art performance with significant improvements across 36 universal MMEB (**3.1\%–8.5\%**) and five visual-interactive SCaR (**15.2\%–20.3\%**) tasks. The code, models, and benchmarks are available at https://github.com/sony/virtue.

Autoregressive (AR) models are promising for image generation, yet continuous-token AR variants often trail latent diffusion and masked-generation models. The core issue is heterogeneous variance in VAE latents, which is amplified during AR decoding, especially under classifier-free guidance (CFG), and can cause variance collapse. We propose SphereAR to address this issue. Its core design is to constrain all AR inputs and outputs---including after CFG---to lie on a fixed-radius hypersphere (constant $\ell_2$ norm), leveraging hyperspherical VAEs. Our theoretical analysis shows that hyperspherical constraint removes the scale component (the primary cause of variance collapse), thereby stabilizing AR decoding. Empirically, on ImageNet generation, SphereAR-H (943M) sets a new state of the art for AR models, achieving FID 1.34. Even at smaller scales, SphereAR-L (479M) reaches FID 1.54 and SphereAR-B (208M) reaches 1.92, matching or surpassing much larger baselines such as MAR-H (943M, 1.55) and VAR-d30 (2B, 1.92). To our knowledge, this is the first time a pure next-token AR image generator with raster order surpasses diffusion and masked-generation models at comparable parameter scales.

Recent advances in few-step generative models (typically $1$-$8$ steps), such as consistency models, have yielded impressive performance. However, their broader adoption is hindered by significant challenges, including substantial computational overhead, the reliance on complex multi-component loss functions, and intricate multi-stage training strategies that lack end-to-end simplicity. These limitations impede their scalability and stability, especially when applied to large-scale models. To address these issues, we introduce **$N$-th order Recursive Consistent velocity field estimation for Generative Modeling (RCGM)**, a novel framework that unifies many existing approaches. Within this framework, we reveal that conventional one-step methods, such as consistency and MeanFlow models, are special cases of 1st-order RCGM. This insight enables a natural extension to higher-order scenarios ($N \geq 2$), which exhibit markedly improved training stability and achieve state-of-the-art (SOTA) performance. For instance, on ImageNet $256\times256$, RCGM enables a $675\text{M}$ parameter diffusion transformer to achieve a $1.48$ FID score in just $2$ sampling steps. Crucially, RCGM facilitates the stable full-parameter training of a large-scale ($20\textrm{B}$) unified multi-modal model, attaining a $0.86$ GenEval score in $2$ steps. In contrast, conventional 1st-order approaches, such as consistency and MeanFlow models, typically suffer from training instability, model collapse, or memory constraints under comparable settings. *Code will be publicly available.*

Current deep learning models for image segmentation often lack reliable uncertainty quantification, particularly at the image-specific level. While Conformal Risk Control (CRC) offers marginal statistical guarantees, achieving image-conditional coverage, which ensures prediction sets reliably capture ground truth for individual images, remains a significant challenge. This paper introduces a novel approach to address this gap by learning image-adaptive thresholds for conformal image segmentation. We first propose AT (Adaptive Thresholding), which frames threshold prediction as a supervised regression task. Building upon the insights from AT, we then introduce COAT (Conditional Optimization for Adaptive Thresholding), an innovative end-to-end differentiable framework. COAT directly optimizes image-conditional coverage by using a soft approximation of the True Positive Rate (TPR) as its loss function, enabling direct gradient-based learning of optimal image-specific thresholds. This novel differentiable miscoverage loss is key to enhancing conditional coverage. Our methods provide a robust pathway towards more trustworthy and interpretable uncertainty estimates in image segmentation, offering improved conditional guarantees crucial for safety-critical applications. The code is available at https://github.com/bjbbbb/Conditional-Optimization-for-Adaptive-Thresholding.

Diffusion models have demonstrated strong potential in language modeling, offering various advantages over traditional autoregressive approaches. Their ability to generate and revise entire responses in parallel enables faster generation and built-in self-correction mechanisms. Most modern diffusion-based language models employ masked diffusion, where decoding involves iteratively processing masked tokens based on a binary decision: either retaining the mask or replacing it with the predicted token. However, this binary choice discards valuable predictive information when the mask is retained. To address this limitation, we introduce soft-masking (SM), a novel method that dynamically blends the embedding of the mask token with the embeddings of the top-k predicted tokens from the previous decoding step, for each retained mask. This provides the model with a more informative prior, preserving context from earlier computations and allowing partial information about masked tokens to propagate beyond a single step. We propose a training methodology that efficiently adapts masked diffusion language models to incorporate SM. We demonstrate that training a 169M parameter model from scratch with SM yields superior perplexity and MAUVE scores compared to binary masking baselines. Similarly, a pretrained model can be enhanced with SM through continued pretraining. Finally, we finetune two state-of-the-art diffusion models, Dream-7B and Dream-Coder-7B, with SM. SM consistently improves performance across multiple coding benchmarks, particularly in high-throughput settings.

Autoregressive image generation aims to predict the next token based on previous ones. However, this process is challenged by the bidirectional dependencies inherent in conventional image tokenizations, which creates a fundamental misalignment with the unidirectional nature of autoregressive models. To resolve this, we introduce AliTok, a novel Aligned Tokenizer that alters the dependency structure of the token sequence. AliTok employs a bidirectional encoder constrained by a causal decoder, a design that compels the encoder to produce a token sequence with both semantic richness and forward-dependency. Furthermore, by incorporating prefix tokens and employing a two-stage tokenizer training process to enhance reconstruction performance, AliTok achieves high fidelity and predictability simultaneously. Building upon AliTok, a standard decoder-only autoregressive model with just 177M parameters achieves a gFID of 1.44 and an IS of 319.5 on ImageNet-256. Scaling to 662M, our model reaches a gFID of 1.28, surpassing the SOTA diffusion method with 10x faster sampling. On ImageNet-512, our 318M model also achieves a SOTA gFID of 1.39. Code and weights at https://github.com/ali-vilab/alitok.

Cross-view completion (CroCo) has proven effective as pre-training for geometric downstream tasks such as stereo depth, optical flow, and point cloud prediction. In this paper we show that it also learns photometric understanding due to training pairs with differing illumination. We propose a method to disentangle CroCo latent representations into a single latent vector representing illumination and patch-wise latent vectors representing intrinsic properties of the scene. To do so, we use self-supervised cross-lighting and intrinsic consistency losses on a dataset two orders of magnitude smaller than that used to train CroCo. This comprises pixel-wise aligned, paired images under different illumination. We further show that the lighting latent can be used and manipulated for tasks such as interpolation between lighting conditions, shadow removal, and albedo estimation. This clearly demonstrates the feasibility of using cross-view completion as pre-training for photometric downstream tasks where training data is more limited.

Image forgery localization in the generative AI era poses new challenges, as modern editing pipelines produce photorealistic, semantically coherent manipulations that evade conventional detectors while model capabilities evolve rapidly. In response, we develop Detective SAM, a framework built on SAM2, a foundation model for image segmentation, that integrates perturbation-driven forensic clues with lightweight feature adapters and a mask adapter to convert forensic clues into forgery masks via automatic prompting. Moreover, to keep up with the rapidly evolving capabilities of diffusion models, we introduce AutoEditForge: an automated diffusion edit generation pipeline spanning four edit types. This supplies high-quality data to maintain localization accuracy under newly released editors and enables continual fine-tuning for Detective SAM. Across seven benchmark datasets and seven baselines, Detective SAM delivers stable out-of-distribution performance, averaging 36.99 IoU / 44.19 F1, a 33.67% relative IoU gain over the best baseline. Further, we show that state-of-the-art edits cause localization systems to collapse. With 500 AutoEditForge samples, Detective SAM quickly adapts and restores performance, enabling practical, low-friction updates as editing models improve. AutoEditForge, Detective SAM's pretrained weights and training script are available at the anonymized repository: https://anonymous.4open.science/r/Detective-SAM-9057/.

Knowledge Editing (KE) is a field that studies how to modify some knowledge in Large Language Models (LLMs) at a low cost (compared to pre-training). Currently, performing large-scale edits on LLMs while ensuring the Reliability, Generality, and Locality metrics of the edits remain a challenge. This paper proposes a Massive editing approach for LLMs based on dynamic weight Generation (MeG). Our MeG involves attaching a dynamic weight neuron to specific layers of the LLMs and using a diffusion model to conditionally generate the weights of this neuron based on the input query required for the knowledge. This allows the use of adding a single dynamic weight neuron to achieve the goal of large-scale knowledge editing. Experiments show that our MeG can significantly improve the performance of large-scale KE in terms of Reliability, Generality, and Locality metrics compared to existing knowledge editing methods, particularly with a high percentage point increase in the absolute value index for the Locality metric, demonstrating the advantages of our proposed method.

Continuous-space video generation has advanced rapidly, while discrete approaches lag behind due to error accumulation and long-context inconsistency. In this work, we revisit discrete generative modeling and present Uniform discRete diffuSion with metric pAth (URSA), a simple yet powerful framework that bridges the gap with continuous approaches for the scalable video generation. At its core, URSA formulates the video generation task as an iterative global refinement of discrete spatiotemporal tokens. It integrates two key designs: a Linearized Metric Path and a Resolution-dependent Timestep Shifting mechanism. These designs enable URSA to scale efficiently to high-resolution image synthesis and long-duration video generation, while requiring significantly fewer inference steps. Additionally, we introduce an asynchronous temporal fine-tuning strategy that unifies versatile tasks within a single model, including interpolation and image-to-video generation. Extensive experiments on challenging video and image generation benchmarks demonstrate that URSA consistently outperforms existing discrete methods and achieves performance comparable to state-of-the-art continuous diffusion methods. Code and models are available at https://github.com/baaivision/URSA.

Generating stylized large language model (LLM) responses via representation editing is a promising way for fine-grained output control. However, there exists an inherent trade-off: imposing a distinctive style often degrades truthfulness. Existing representation editing methods, by naively injecting style signals, overlook this collateral impact and frequently contaminate the model’s core truthfulness representations, resulting in reduced answer correctness. We term this phenomenon stylization-induced truthfulness collapse. We attribute this issue to latent coupling between style and truth directions in certain key attention heads, and propose \textbf{StyliTruth}, a mechanism that preserves stylization while keeping truthfulness intact. StyliTruth separates the style-relevant and truth-relevant subspaces in the model’s representation space via an orthogonal deflation process. This decomposition enables independent control of style and truth in their own subspaces, minimizing interference. By designing adaptive, token-level steering vectors within each subspace, we dynamically and precisely control the generation process to maintain both stylistic fidelity and truthfulness. We validate our method on multiple styles and languages. Extensive experiments and analyses show that StyliTruth significantly reduces stylization-induced truthfulness collapse and outperforms existing inference-time intervention methods in balancing style adherence with truthfulness.

In recent years, integrating multimodal understanding and generation into a single unified model has emerged as a promising paradigm. While this approach achieves strong results in text-to-image (T2I) generation, it still struggles with precise image editing. We attribute this limitation to an imbalanced division of responsibilities. The understanding module primarily functions as a translator that encodes user instructions into semantic conditions, while the generation module must simultaneously act as designer and painter, inferring the original layout, identifying the target editing region, and rendering the new content. This imbalance is counterintuitive because the understanding module is typically trained with several times more data on complex reasoning tasks than the generation module. To address this issue, we introduce *Draw-In-Mind* (DIM), a dataset comprising two complementary subsets: (**i**) DIM-T2I, containing 14M long-context image–text pairs to enhance complex instruction comprehension; and (**ii**) DIM-Edit, consisting of 233K chain-of-thought imaginations generated by GPT-4o, serving as explicit design blueprints for image edits. We connect a frozen Qwen2.5-VL-3B with a trainable SANA1.5-1.6B via a lightweight two-layer MLP, and train it on the proposed DIM dataset, resulting in DIM-4.6B-T2I/Edit. Despite its modest parameter scale, DIM-4.6B-Edit achieves SOTA or competitive performance on the ImgEdit and GEdit-Bench benchmarks, outperforming much larger models such as UniWorld-V1 and Step1X-Edit. These findings demonstrate that explicitly assigning the design responsibility to the understanding module provides significant benefits for image editing. Our dataset and models will be publicly available.

Graph generation is a critical yet challenging task as empirical analyses require a deep understanding of complex, non-Euclidean structures. Diffusion models have recently made significant achievements in graph generation, but these models are typically adapted from image generation frameworks and overlook inherent higher-order topology, leaving them ill-suited for capturing the topological properties of graphs. In this work, we propose Higher-order Guided Diffusion (HOG-Diff), a principled framework that progressively generates plausible graphs with inherent topological structures. HOG-Diff follows a coarse-to-fine generation curriculum guided by higher-order topology and implemented via diffusion bridges. We further prove that our model exhibits a stronger theoretical guarantee than classical diffusion frameworks. Extensive experiments on both molecular and generic graph generation tasks demonstrate that our method consistently outperforms or remains competitive with state-of-the-art baselines.

Generative models have demonstrated significant results in ultra-low bitrate image compression, owing to their powerful capabilities for content generation and texture completion. Existing works primarily based on diffusion models still face challenges such as limited bitrate adaptability and high computational complexity for encoding and decoding. Inspired by the success of Visual AutoRegressive model (VAR), we introduce AutoRegressive-based Progressive Coding (ARPC) for ultra-low bitrate image compression, a progressive image compression framework based on next-scale prediction visual autoregressive model. Based on multi-scale residual vector quantizer, ARPC efficiently encodes the image into multi-scale discrete token maps and controls the bitrates by selecting different scales for transmission. For decompression, ARPC leverages the prior knowledge inherent in the visual autoregressive model to predict the unreceived scales, which is naturally the autoregressive generation process. To further increase the compression ratio, we target the VAR as a probability estimator for lossless entropy coding and propose group-masked bitwise multi-scale residual quantizer to adaptively allocate bits for different scales. Extensive experiments show that ARPC achieves state-of-the-art perceptual fidelity at ultra-low bitrates and high decompression efficiency compared with existing diffusion-based methods.