ICLR 2026 论文列表

We address the challenge of efficient auto-regressive generation in sequence prediction models by introducing FutureFill—a general-purpose fast generation method for any sequence prediction algorithm based on convolutional operators. FutureFill reduces generation time from quadratic to quasilinear in the context length. Moreover, when generating from a prompt, it requires a prefill cache whose size grows only with the number of tokens to be generated—often much smaller than the caches required by standard convolutional or attention‐based models. We validate our theoretical claims with language modeling experiments and demonstrate substantial efficiency gains when generating from a deep convolutional sequence prediction model.

Several companies have deployed watermark-based detection to identify AI-generated content. However, attribution--the ability to trace back to the user of a generative AI (GenAI) service who created the given AI-generated content--remains largely unexplored despite its growing importance. In this work, we aim to bridge this gap by conducting the first systematic study on watermark-based, user-level attribution of AI-generated content. Our key idea is to assign a unique watermark to each user of the GenAI service and embed this watermark into the AI-generated content created by that user. Attribution is then performed by identifying the user whose watermark best matches the one extracted from the given content. This approach, however, faces a key challenge: How should watermarks be selected for users to maximize attribution performance? To address the challenge, we first theoretically derive lower bounds on detection and attribution performance through rigorous probabilistic analysis for any given set of user watermarks. Then, we select watermarks for users to maximize these lower bounds, thereby optimizing detection and attribution performance. Our theoretical and empirical results show that watermark-based attribution inherits both the accuracy and (non-)robustness properties of the underlying watermark. Specifically, attribution remains highly accurate when the watermarked AI-generated content is either not post-processed or subjected to common post-processing such as JPEG compression, as well as black-box adversarial post-processing with limited query budgets.

Recent methods have made notable progress in accelerating Large Vision-Language Models (LVLMs) by exploiting the inherent redundancy in visual inputs. Most existing approaches, however, focus narrowly on reducing image tokens before or within the Large Language Model (LLM) stage to lower computational cost. This overlooks other major bottlenecks, particularly the image encoder, which itself requires substantial computation. As a result, these methods fall short of achieving true end-to-end acceleration. Importantly, the image encoder is the primary contributor of input tokens to the LLM. Thus, reducing visual redundancy at the encoder stage not only speeds up the encoder itself but also significantly lightens the workload for the subsequent LLM. Motivated by this, we investigate how to jointly optimize the image encoder and the LLM along with other LVLM components for comprehensive acceleration. To mitigate the risk of performance degradation from token reduction, we propose a novel token merging strategy that recycles useful information from otherwise discarded tokens. Our approach, iLLaVA, delivers consistent improvements across both image and video understanding tasks, achieving up to a 2× throughput boost and a 4× reduction in prefilling time. Notably, iLLaVA enables a larger model (e.g., InternVL-2.5 26B) to surpass a smaller counterpart (e.g., InternVL-2.5 8B) in both accuracy and efficiency. Extensive comparisons with state-of-the-art token pruning and merging techniques demonstrate the clear superiority of our method. Finally, we provide detailed visualizations for the merging steps of iLLaVA , offering deeper insights into how different LVLM components contribute to efficient computation.

Non-autoregressive (NAR) language models offer notable efficiency in text generation by circumventing the sequential bottleneck of autoregressive decoding. However, accurately modeling dependencies in discrete sequences remains challenging in this paradigm. In this work, we advance the field of NAR generation by applying conditional flow matching (CFM) methods grounded in geometrically principled interpolation, specifically leveraging Kullback-Leibler (KL) divergence geodesics, which correspond to linear interpolation in logit space. We rigorously establish that maximizing conditional likelihood in this setting precisely recovers the flow matching velocity field, supplying the theoretical justification for this approach in sequence modeling. To address practical performance gaps of \emph{basic} inference, we propose a novel empirical \emph{sampling} strategy that iteratively denoises and re-noises, along with a \emph{hybrid} scheme that integrates our \emph{sampling} method with \emph{basic} procedure. Across unconditional and conditional text and code infilling, the approach improves perplexity and downstream metrics over prior NAR baselines under matched settings.

Recent studies on 3D hand reconstruction have demonstrated the effectiveness of synthetic training data to improve estimation performance. However, most methods rely on game engines to synthesize hand images, which often lack diversity in textures and environments, and fail to include crucial components like arms or interacting objects. Generative models are promising alternatives to generate diverse hand images, but still suffer from misalignment issues. In this paper, we present SesaHand, which enhances controllable hand image generation from both semantic and structural alignment perspectives for 3D hand reconstruction. Specifically, for semantic alignment, we propose a pipeline with Chain-of-Thought inference to extract human behavior semantics from image captions generated by the Vision-Language Model. This semantics suppresses human-irrelevant environmental details and ensures sufficient human-centric contexts for hand image generation. For structural alignment, we introduce hierarchical structural fusion to integrate structural information with different granularity for feature refinement to better align the hand and the overall human body in generated images. We further propose a hand structure attention enhancement method to efficiently enhance the model's attention on hand regions. Experiments demonstrate that our method not only outperforms prior work in generation performance but also improves 3D hand reconstruction with the generated hand images.

Visual Autoregressive (VAR) models enhance generation speed but face a critical efficiency bottleneck in later stages. In this paper, we present a novel optimization framework for VAR models that fundamentally differs from prior approaches such as FastVAR and SkipVAR. Instead of relying on heuristic skipping strategies, our method leverages attention entropy to characterize the semantic projections across different dimensions of the model architecture. This enables precise identification of parameter dynamics under varying token granularity levels, semantic scopes, and generation scales. Building on this analysis, we further uncover sparsity patterns along three critical dimensions—token, layer, and scale—and propose a set of fine-grained optimization strategies tailored to these patterns. Extensive evaluation demonstrates that our approach achieves aggressive acceleration of the generation process while significantly preserving semantic fidelity and fine details, outperforming traditional methods in both efficiency and quality. Experiments on Infinity-2B and Infinity-8B models demonstrate that ToProVAR achieves nearly 3.5× average acceleration with minimal quality loss, effectively mitigating the issues found in prior work. Our code will be made publicly available.

Eigenvalue problems are among the most important topics in many scientific disciplines. With the recent surge and development of machine learning, neural eigenvalue methods have attracted significant attention as a forward pass of inference requires only a tiny fraction of the computation time compared to traditional solvers. However, a key limitation is the requirement for large amounts of labeled data in training, including operators and their eigenvalues. To tackle this limitation, we propose a novel method, named **S**orting **C**hebyshev **S**ubspace **F**ilter (**SCSF**), which significantly accelerates eigenvalue data generation by leveraging similarities between operators---a factor overlooked by existing methods. Specifically, SCSF employs truncated fast Fourier transform (FFT) sorting to group operators with similar eigenvalue distributions and constructs a Chebyshev subspace filter that leverages eigenpairs from previously solved problems to assist in solving subsequent ones, reducing redundant computations. To the best of our knowledge, SCSF is the first method to accelerate eigenvalue data generation. Experimental results show that SCSF achieves up to a $3.5\times$ speedup compared to various numerical solvers.

Creating novel images by fusing visual cues from multiple sources is a fundamental yet underexplored problem in image-to-image generation, with broad applications in artistic creation, virtual reality and visual media. Existing methods often face two key challenges: coexistent generation, where multiple objects are simply juxtaposed without true integration, and bias generation, where one object dominates the output due to semantic imbalance. To address these issues, we propose **Visual Mixing Diffusion (VMDiff)**, a simple yet effective diffusion-based framework that synthesizes a single, coherent object by integrating two input images at both noise and latent levels. Our approach comprises: (1) a **hybrid sampling process** that combines guided denoising, inversion, and spherical interpolation with adjustable parameters to achieve structure-aware fusion, mitigating coexistent generation; and (2) an **efficient adaptive adjustment module**, which introduces a novel similarity-based score to automatically and adaptively search for optimal parameters, countering semantic bias. Experiments on a curated benchmark of 780 concept pairs demonstrate that our method outperforms strong baselines in visual quality, semantic consistency, and human-rated creativity.

Video generation models have achieved remarkable progress in creating high-quality, photorealistic content. However, their ability to accurately simulate physical phenomena remains a critical and unresolved challenge. This paper presents $PhyWorldBench$ , a comprehensive benchmark designed to evaluate video generation models based on their adherence to the laws of physics. The benchmark covers multiple levels of physical phenomena, ranging from fundamental principles like object motion and energy conservation to more complex scenarios involving rigid body interactions and human or animal motion. Additionally, we introduce a novel "Anti-Physics" category, where prompts intentionally violate real-world physics, enabling the assessment of whether models can follow such instructions while maintaining logical consistency. Besides large-scale human evaluation, we also design a simple yet effective method that could utilize current MLLM to evaluate the physics realism in a zero-shot fashion. We evaluate 10 state-of-the-art text-to-video generation models, including five open-source and five proprietary models, with a detailed comparison and analysis. we identify pivotal challenges models face in adhering to real-world physics. Through systematic testing of their outputs across 1,050 curated prompts—spanning fundamental, composite, and anti-physics scenarios—we identify pivotal challenges these models face in adhering to real-world physics. We then rigorously examine their performance on diverse physical phenomena with varying prompt types, deriving targeted recommendations for crafting prompts that enhance fidelity to physical principles.

Vision-language models for medical image segmentation often produce masks that conflict with the accompanying text, especially under multi-site/multi-lesion descriptions. We trace this failure to two factors: (i) highly templated and repetitive clinical language causes one-to-one hard contrastive learning to yield numerous false negatives, weakening cross-modal alignment; and (ii) predominantly vision-driven, one-way cross-attention lacks a language-dominant, spatially aware pathway, hindering effective injection of textual semantics into the spatial visual domain. To this end, we propose Consistency-enhanced Two-stage Segmentation (C2Seg). In the pretraining stage, Cluster-aware Contrastive Learning uses a frozen strong baseline to construct an intra-batch text similarity matrix as soft labels, thereby alleviating false negative conflicts and producing more discriminative visual representations. In the fusion stage, we introduce a Bidirectional Complementary Attention Module, where each modality dominates attention along its own path, fostering deep interaction and structural consistency between visual and textual representations. In order to enhance the expressive power of multimodal features, we further adopt KAN-based Attention Gating. Without updating the language encoder, our approach significantly improves text-mask consistency and segmentation accuracy on four public medical imaging datasets. Code is provided in the supplementary material.

Consistent text-to-image (T2I) generation seeks to produce identity-preserving images of the same subject across diverse scenes, yet it often fails due to a phenomenon called identity (ID) shift. Previous methods have tackled this issue, but typically rely on the unrealistic assumption of knowing all target scenes in advance. This paper reveals that a key source of ID shift is the native correlation between subject and scene context, called scene contextualization, which arises naturally as T2I models fit the training distribution of vast natural images. We formally prove the near-universality of this scene-subject correlation and derive theoretical bounds on its strength. On this basis, we propose a novel, efficient, training-free prompt embedding editing approach, called Scene De-Contextualization (SDeC), that imposes an inversion process of T2I’s built-in scene contextualization. Specifically, it identifies and suppresses the latent scene-subject correlation within the ID prompt’s embedding by quantifying SVD directional stability to re-weight the corresponding eigenvalues adaptively. Critically, SDeC allows for per-scene use (one prompt per scene) without requiring prior access to all target scenes. This makes it a highly flexible and general solution well-suited to real-world applications where such prior knowledge is often unavailable or varies over time. Experiments demonstrate that SDeC significantly enhances identity preservation while maintaining scene diversity.

We introduce ARPG, a novel visual Autoregressive model that enables Randomized Parallel Generation, addressing the inherent limitations of conventional raster-order approaches, which hinder inference efficiency and zero-shot generalization due to their sequential, predefined token generation order. Our key insight is that effective random-order modeling necessitates explicit guidance for determining the position of the next predicted token. To this end, we propose a novel decoupled decoding framework that decouples positional guidance from content representation, encoding them separately as queries and key-value pairs. By directly incorporating this guidance into the causal attention mechanism, our approach enables fully random-order training and generation, eliminating the need for bidirectional attention. Consequently, ARPG readily generalizes to zero-shot tasks such as image in-painting, out-painting, and resolution expansion. Furthermore, it supports parallel inference by concurrently processing multiple queries using a shared KV cache. On the ImageNet-1K 256 benchmark, our approach attains an FID of 1.83 with only 32 sampling steps, achieving over a 30 times speedup in inference and and a 75 percent reduction in memory consumption compared to representative recent autoregressive models at a similar scale.

A primary bottleneck in large-scale text-to-video generation today is physical consistency and controllability. Despite recent advances, state-of-the-art models often produce unrealistic motions, such as objects falling upward, or abrupt changes in velocity and direction. Moreover, these models lack precise parameter control, struggling to generate physically consistent dynamics under different initial conditions. We argue that this fundamental limitation stems from current models learning motion distributions solely from appearance, while lacking an understanding of the underlying dynamics. In this work, we propose NewtonGen, a framework that integrates data-driven synthesis with learnable physical principles. At its core lies trainable Neural Newtonian Dynamics (NND), which can model and predict a variety of Newtonian motions, thereby injecting latent dynamical constraints into the video generation process. By jointly leveraging data priors and dynamical guidance, NewtonGen enables physically consistent video synthesis with precise parameter control. All data and code will be public.

Video-conditioned 4D shape generation aims to recover time-varying 3D geometry and view-consistent appearance directly from an input video. In this work, we introduce a native video-to-4D shape generation framework that synthesizes a single dynamic 3D representation end-to-end from the video. Our framework introduces three key components based on large-scale pre-trained 3D models: (i) a temporal attention that conditions generation on all frames while producing a time-indexed dynamic representation; (ii) a time-aware point sampling and 4D latent anchoring that promote temporally consistent geometry and texture; and (iii) noise sharing across frames to enhance temporal stability. Our method accurately captures non-rigid motion, volume changes, and even topological transitions without per-frame optimization. Across diverse in-the-wild videos, our method improves robustness and perceptual fidelity and reduces failure modes compared with the baselines.

Image autoregressive models (IARs) have recently demonstrated remarkable capabilities in visual content generation, achieving photorealistic quality and rapid synthesis through the next-token prediction paradigm adapted from large language models. As these models become widely accessible, robust data provenance is required to reliably trace IAR-generated images to the source model that synthesized them. This is critical to prevent the spread of misinformation, detect fraud, and attribute harmful content. We find that although IAR-generated images often appear visually identical to real images, their generation process introduces characteristic patterns in their outputs, which serves as a reliable provenance signal for the generated images. Leveraging this, we present a post-hoc framework that enables the robust detection of such patterns for provenance tracing. Notably, our framework does not require modifications of the generative process or outputs. Thereby, it is applicable in contexts where prior watermarking methods cannot be used, such as for generated content that is already published without additional marks and for models that do not integrate watermarking. We demonstrate the effectiveness of our approach across a wide range of IARs, highlighting its high potential for robust data provenance tracing in autoregressive image generation.

Designing system algorithms remains challenging, where the discontinuous nature of the solution space often forces system engineers to rely on generic heuristics at the expense of performance. We study whether LLMs can practically drive algorithm generation, and find that they are biased towards well-known generic designs, rather than making the creative leaps needed to navigate the discontinuous solution space. To address this limitation, we introduce MetaMuse, a framework for creative ideation built on three self-reflection principles: (1) quantifying solution diversity and usefulness in measurable performance space, rather than abstract idea space, (2) steering ideation through external stimuli, rather than internal randomness, and (3) constructing executable solutions using waypoint reasoning, rather than free-form chain-of-thought. Extensive evaluation shows that MetaMuse can generate high-performing solutions for two critical problems at a global cloud provider: cache replacement (reducing cache misses by up to 35.76%) and online bin packing (reducing bin usage by up to 30.93%).

Masked Autoregressive (MAR) models promise better efficiency in visual generation than continuous autoregressive (AR) models for the ability of parallel generation, yet their acceleration potential remains constrained by the modeling complexity of spatially correlated visual tokens in a single step. To address this limitation, we introduce Generation then Reconstruction (GtR), a training-free hierarchical sampling strategy that decomposes generation into two stages: structure generation establishing global semantic scaffolding, followed by detail reconstruction efficiently completing remaining tokens. Assuming that it is more difficult to create an image from scratch than to complement images based on a basic image framework, GtR is designed to achieve acceleration by computing the reconstruction stage quickly while maintaining the generation quality by computing the generation stage slowly. Moreover, observing that tokens on the details of an image often carry more semantic information than tokens in the salient regions, we further propose Frequency-Weighted Token Selection (FTS) to offer more computation budget to tokens on image details, which are localized based on the energy of high frequency information. Extensive experiments on ImageNet class-conditional and text-to-image generation demonstrate 3.72$\times$ speedup on MAR-H while maintaining comparable quality (e.g., FID: 1.59, IS: 304.4 vs. original 1.59, 299.1), substantially outperforming existing acceleration methods across various model scales and generation tasks. Our codes have been released in supplementary materials and will be released on Github.

Recent advancements in Large Multimodal Models (LMMs) have significantly improved multimodal understanding and generation. However, these models still struggle to generate tightly interleaved image-text outputs, primarily due to the limited scale, quality and instructional richness of current training datasets. To address this, we introduce \textbf{InterSyn}, a dataset that features: (1) large scale, comprising 1.8M multimodal samples; (2) high quality, supported by our proposed \textbf{Self-Evaluation with Iterative Refinement (SEIR)} method for rigorous automated quality refinement; (3) rich instructional diversity, ensured through diverse well-designed question templates, based on human preferences and covering a 3500-topic hierarchy. These characteristics make InterSyn particularly well-suited for training LMMs in interactive image–text generation capabilities. To evaluate the capabilities, we propose \textbf{SynJudge}, a reliable automatic evaluator that aligns closely with human judge and outputs four interpretable scores: Text Content Completeness (TCC), Image Content Completeness (ICC), Image Quality (IQ), and Image–Text Synergy (ITS). These scores are complementary, covering both content and quality as well as cross-modal interaction, thereby forming a comprehensive evaluation framework. Experimental results on InterSyn subsets of up to 200K samples show that 25K–50K already yield substantial improvements, while scaling to 100K/200K brings further gains in TCC, ICC, and especially ITS, highlighting InterSyn’s: (1) scalability, as performance consistently improves with more data; (2) efficiency, as significant gains are achievable even with smaller subsets, making it accessible to researchers with varying computational resources.

Generating graph-structured data is crucial in applications such as molecular generation, knowledge graphs, and network analysis. However, their discrete, unordered nature makes them difficult for traditional generative models, leading to the rise of discrete diffusion and flow matching models. In this work, we introduce GraphBSI, a novel one-shot graph generative model based on Bayesian Sample Inference (BSI). Instead of evolving samples directly, GraphBSI iteratively refines a belief over graphs in the continuous space of distribution parameters, naturally handling discrete structures. Further, we state BSI as a stochastic differential equation (SDE) and derive a noise-controlled family of SDEs that preserves the marginal distributions via an approximation of the score function. Our theoretical analysis further reveals the connection to Bayesian Flow Networks and Diffusion models. Finally, in our empirical evaluation, we demonstrate state-of-the-art performance on molecular and synthetic graph generation, outperforming existing one-shot graph generative models on the standard benchmarks Moses and GuacaMol.