ICLR 2026 论文列表

We introduce BézierFlow, a lightweight training approach for few-step generation with pretrained diffusion and flow models. BézierFlow achieves a 2–3× performance improvement for sampling with $\leq$ 10 NFEs while requiring only 15 minutes of training. Recent lightweight training approaches have shown promise by learning optimal timesteps, but their scope remains restricted to ODE discretizations. To broaden this scope, we propose learning the optimal transformation of the sampling trajectory by parameterizing stochastic interpolant (SI) schedulers. The main challenge lies in designing a parameterization that satisfies critical desiderata, including boundary conditions, differentiability, and monotonicity of the SNR. To effectively meet these requirements, we represent scheduler functions as Bézier functions, where control points naturally enforce these properties. This reduces the problem to learning an ordered set of points in the time range, while the interpretation of the points changes from ODE timesteps to Bézier control points. Across a range of pretrained diffusion and flow models, BézierFlow consistently outperforms prior timestep-learning methods, demonstrating the effectiveness of expanding the search space from discrete timesteps to Bézier-based trajectory transformations.

Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumulation and long inference times. In this work, we propose a distillation-based framework for efficient causal video generation that enables high-quality synthesis with extreme limited denoising steps. Our approach builds upon Distribution Matching Distillation (DMD) framework and proposes a novel form of Adversarial Self-Distillation (ASD) strategy, which aligns the outputs of the student model's $n$-step denoising process with its $(n+1)$-step version in the distribution level. This design provides smoother supervision by bridging small intra-student gaps and more informative guidance by combining teacher knowledge with locally consistent student behavior, substantially improving training stability and generation quality in extremely few-step scenarios. In addition, we present a First-Frame Enhancement (FFE) strategy, which allocates more denoising steps to the initial frames to mitigate error propagation while applying larger skipping steps to later frames. Extensive experiments on VBench demonstrate that our method surpasses state-of-the-art approaches in both one-step and two-step video generation. Notably, our framework produces a single distilled model that flexibly supports multiple inference-step settings, eliminating the need for repeated re-distillation and enabling efficient, high-quality video synthesis.

Human mobility trajectory data supports a wide range of applications, including urban planning, intelligent transportation systems, and public safety monitoring. However, large-scale, high-quality mobility datasets are difficult to obtain due to privacy concerns. Raw trajectory data may reveal sensitive user information, such as home addresses, routines, or social relationships, making it crucial to develop privacy-preserving alternatives. Recent advances in deep generative modeling have enabled synthetic trajectory generation, but existing methods either lack formal privacy guarantees or suffer from reduced utility and scalability. Differential Privacy (DP) has emerged as a rigorous framework for data protection, and recent efforts such as PATE-GAN and PATEGAIL integrate DP with generative adversarial learning. While promising, these methods struggle to generalize across diverse trajectory patterns and often incur significant utility degradation. In this work, we propose a new framework that builds on PATEGAIL by introducing a sensitivity-aware noise injection module that dynamically adjusts privacy noise based on sample-level sensitivity. This design significantly improves trajectory fidelity, downstream task performance, and scalability under strong privacy guarantees. We evaluate our method on real-world mobility datasets and demonstrate its superiority over state-of-the-art baselines in terms of privacy-utility trade-off.

Hallucinations are a common issue that undermine the reliability of large language models (LLMs). Recent studies have identified a specific subset of hallucinations, known as confabulations, which arise due to predictive uncertainty of LLMs. To detect confabulations, various methods for estimating predictive uncertainty in natural language generation (NLG) have been developed. These methods are typically evaluated by correlating uncertainty estimates with the correctness of generated text, with question-answering (QA) datasets serving as the standard benchmark. However, commonly used approximate correctness functions have substantial disagreement between each other and, consequently, in the ranking of the uncertainty estimation methods. This allows one to inflate the apparent performance of uncertainty estimation methods. We propose using several alternative risk indicators for risk correlation experiments that improve robustness of empirical assessment of UE algorithms for NLG. For QA tasks, we show that marginalizing over multiple LLM-as-a-judge variants leads to reducing the evaluation biases. Furthermore, we explore structured tasks as well as out of distribution and perturbation detection tasks which provide robust and controllable risk indicators. Finally, we propose to use an Elo rating of uncertainty estimation methods to give an objective summarization over extensive evaluation settings.

Diffusion-based video generation can create realistic videos, yet existing image and text-based conditioning fails to offer precise motion control. Prior methods for motion control typically rely on displacement-based conditioning and require model-specific fine-tuning, which is computationally expensive and restrictive. We introduce Time-to-Move (TTM), a training-free, plug-and-play framework for motion- and appearance-controlled video generation with image-to-video (I2V) diffusion models. Our key insight is to use crude reference animations, obtained through user-friendly manipulations such as cut-and-drag or depth-based reprojection, as direct motion guidance, analogous to using coarse layout input in image editing. To integrate these signals, we adapt SDEdit to the video domain while anchoring the appearance with image conditioning. We further propose dual-clock denoising, a region-dependent strategy that enforces strong alignment in motion-specified regions and grants flexibility elsewhere, balancing fidelity to user intent with natural dynamics. This lightweight modification of the sampling process incurs no additional training or runtime cost and is compatible with any backbone. Extensive experiments on object and camera motion benchmarks show that TTM matches or exceeds existing training-based baselines in realism and motion control. Beyond this, TTM introduces a unique capability: precise appearance control through pixel-level conditioning, exceeding the limits of text-only prompting.

Large language models (LLMs) are increasingly used in modern search and answer systems to synthesize multiple, sometimes conflicting, texts into a single response, yet current pipelines offer weak incentives for sources to be accurate and are vulnerable to adversarial content. We introduce Truthful Text Summarization (TTS), an incentive-aligned framework that improves factual robustness without ground-truth labels. TTS (i) decomposes a draft synthesis into atomic claims, (ii) elicits each source’s stance on every claim, (iii) scores sources with an adapted multi-task peer-prediction mechanism that rewards informative agreement, and (iv) filters unreliable sources before re-summarizing. We establish formal guarantees that align a source’s incentives with informative honesty, making truthful reporting the utility-maximizing strategy. Experiments show that TTS improves factual accuracy and robustness while preserving fluency, aligning exposure with informative corroboration and disincentivizing manipulation.

Controllable video generation remains a significant challenge, despite recent advances in generating high-quality and consistent videos. Most existing methods for controlling video generation treat the video as a whole, neglecting intricate fine-grained spatiotemporal relationships, which limits both control precision and efficiency. In this paper, we propose \textbf{Co}ntrollable \textbf{V}ide\textbf{o} \textbf{G}enerative \textbf{A}dversarial \textbf{N}etworks (\ourmes) to disentangle the video concepts, thus facilitating efficient and independent control over individual concepts. Specifically, following the \textbf{minimal change principle}, we first disentangle static and dynamic latent variables. We then leverage the \textbf{sufficient change property} to achieve component-wise identifiability of dynamic latent variables, enabling independent control over motion and identity. To establish the theoretical foundation, we provide a rigorous analysis demonstrating the identifiability of our approach. Building on these theoretical insights, we design a \textbf{Temporal Transition Module} to disentangle latent dynamics. To enforce the minimal change principle and sufficient change property, we minimize the dimensionality of latent dynamic variables and impose temporal conditional independence. To validate our approach, we integrate this module as a plug-in for GANs. Extensive qualitative and quantitative experiments on various video generation benchmarks demonstrate that our method significantly improves generation quality and controllability across diverse real-world scenarios.

Computational replication of Chinese calligraphy, a cornerstone of cultural heritage, remains challenging. Existing methods split into two flawed camps: some render high-quality isolated characters yet miss page-level aesthetics (ligatures, spacing, scale), while others attempt page/column synthesis but sacrifice calligraphic correctness. We introduce UniCalli, a unified diffusion framework for column-level recognition and generation. Training both tasks in one model is deliberate: recognition constrains the generator to preserve character identity and stroke structure, while generation supplies strong style/layout priors—together fostering concept-level abstractions (radicals, stroke configurations) that improve both tasks under long-tail, limited-label regimes. We curate a dataset of 8,000+ digitized pieces, with ~4,000 densely annotated (script labels, character boxes, transcriptions). UniCalli employs asymmetric noising and a rasterized box map to inject spatial priors, and is trained on a mix of synthetic, labeled, and unlabeled data. The model is robust to rare styles, better disentangles style from script, and attains state-of-the-art generative quality with clear gains in ligature continuity and layout fidelity, alongside stronger recognition. The framework extends to other ancient scripts, demonstrated by successful transfer to Oracle bone inscriptions and Egyptian hieroglyphs. Code and data will be released.

Generating coherent and communicative visual sequences, such as image sequences and videos, remains a significant challenge for current multimodal systems. Despite advances in visual quality and the integration of world knowledge, existing models still struggle to maintain logical flow, often resulting in disjointed actions, fragmented narratives, and unclear storylines. We attribute these issues to the lack of attention to visual logic, a critical yet underexplored dimension of visual sequence generation that we define as the perceptual and causal coherence among characters, actions, and scenes over time. To bridge this gap, we propose a logic-aware multi-image story visualization framework, LogiStory. The framework is built around the central innovation of explicitly modeling visual logic in story visualization. To realize this idea, we design a multi-agent system that grounds roles, extracts causal chains, and verifies story-level consistency, transforming narrative coherence from an implicit byproduct of image generation into an explicit modeling objective. This design effectively bridges structured story planning with visual generation, enhancing both narrative clarity and visual quality in story visualization. Furthermore, to evaluate the generation capacity, we construct LogicTale, a benchmark comprising richly annotated stories, emphasizing causal reasoning, and visual logic interpretability. We establish comprehensive automatic and human evaluation protocols designed to measure both visual logic and perceptual quality. Experiments demonstrate that our approach significantly improves the narrative logic of generated visual stories. This work provides a foundational step towards modeling and enforcing visual logic in general image sequence and video generation tasks.

The digital industry demands high-quality, diverse modular 3D assets, especially for user-generated content (UGC). In this work, we introduce AssetFormer, an autoregressive Transformer-based model designed to generate modular 3D assets from textual descriptions. Our pilot study leverages real-world modular assets collected from online platforms. AssetFormer tackles the challenge of creating assets composed of primitives that adhere to constrained design parameters for various applications. By innovatively adapting module sequencing and decoding techniques inspired by language models, our approach enhances asset generation quality through autoregressive modeling. Initial results indicate the effectiveness of AssetFormer in streamlining asset creation for professional development and UGC scenarios. This work presents a flexible framework extendable to various types of modular 3D assets, contributing to the broader field of 3D content generation. The code is available at https://github.com/Advocate99/AssetFormer.

Diffusion transformers currently lead the field in high-quality video generation, but their slow iterative denoising process and prohibitive quadratic attention costs for long sequences create significant inference bottlenecks. While both step distillation and sparse attention mechanisms have shown promise as independent acceleration strategies, effectively combining these approaches presents critical challenges---training-free integration yields suboptimal results, while separately training sparse attention after step distillation requires prohibitively expensive high-quality video data. To overcome these limitations, we propose $\textit{BLADE}$, an innovative data-free joint training framework that introduces: (1) an Adaptive Block-Sparse Attention (ASA) mechanism for dynamically generating content-aware sparsity masks to focus computation on salient spatiotemporal features, and (2) a sparsity-aware step distillation paradigm, built upon Trajectory Distribution Matching (TDM), directly incorporates sparsity into the distillation process rather than treating it as a separate compression step and features fast convergence. We validate BLADE on text-to-video models like CogVideoX-5B and Wan2.1-1.3B, and our framework demonstrates remarkable efficiency gains across different scales. On Wan2.1-1.3B, BLADE achieves a 14.10$\times$ end-to-end inference acceleration over a 50-step baseline. Moreover, on models such as CogVideoX-5B with short video sequence lengths, our framework delivers a robust 8.89$\times$ speedup. Crucially, the acceleration is accompanied by a consistent quality improvement. On the VBench-2.0 benchmark, BLADE boosts the score of CogVideoX-5B to 0.569 (from 0.534) and Wan2.1-1.3B to 0.570 (from 0.563), results that are further corroborated by superior ratings in human evaluations.

In this work, we propose K-Flow, a novel generative learning paradigm that flows along the $K$-amplitude domain, where $K$ is a scaling parameter that organizes projected coefficients (frequency bands), and amplitude refers to the norm of such coefficients. We instantiate K-Flow with three concrete $K$-amplitude transformations: Fourier transformation, Wavelet transformation, and PCA. By incorporating the $K$-amplitude transformations, K-Flow enables flow matching across the scaling parameter as time. We discuss six properties of K-Flow, covering its theoretical foundations, energy and temporal dynamics, and practical applications. Specifically, from the perspective of practical usage, K-Flow allows for steerable generation by controlling the information at different scales. To demonstrate the effectiveness of K-Flow, we conduct experiments on both unconditional and conditional image generation tasks, showing that K-Flow achieves competitive performance. Furthermore, we perform three ablation studies to illustrate how K-Flow leverages the scaling parameter for controlled image generation. Additional results, including scientific applications, are also provided.

Recently, diffusion models have been recognized as state-of-the-art models for image generation due to their ability to produce high-quality images. However, recent studies have shown that diffusion models are susceptible to backdoor attacks, where an attacker can activate hidden biases using a specific trigger pattern, causing the model to generate a predefined target. Fortunately, executing backdoor attacks is still challenging, as they typically require substantial time and memory to perform parameter-based fine-tuning. In this paper, we are the first to reveal the **spatio-temporal redundancy** in backdoor attacks on diffusion models. **Regarding spatial redundancy**, we observed the *enrichment phenomenon*, which reflects the abnormal gradient accumulation induced by backdoor injection. **Regarding temporal redundancy**, we observed a marginal effect associated with specific time steps, indicating that only a limited subset of time steps plays a critical role in backdoor injection. Building on these findings, we present a novel framework, *STEDiff*, comprising two key components: *STEBA* and *STEDF*. *STEBA* is a spatio-temporally efficient accelerated attack strategy that achieves up to **15.07×** speedup in backdoor injection while reducing GPU memory usage by **82%**. *STEDF* is a detection framework leveraging spatio-temporal features, by modeling the enrichment phenomenon in weights and anisotropy across time steps, which achieves a backdoor detection rate of up to **99.8%**. Our code is available at: [https://github.com/paoche11/STEDiff](https://github.com/paoche11/STEDiff).

We propose to improve multi-concept prompt fidelity in text-to-image diffusion models. We begin with common failure cases—prompts like “a cat and a clock” that sometimes yields images where one concept is missing, faint, or colliding awkwardly with another. We hypothesize that this happens when the diffusion model drifts into mixed modes that over-emphasize a single concept it learned strongly during training. Instead of re-training, we introduce a corrective sampling strategy that steers away from regions where the joint prompt behavior overlaps too strongly with any single concept in the prompt. The goal is to steer towards “pure” joint modes where all concepts can coexist with balanced visual presence. We further show that existing multi-concept guidance schemes can operate in unstable weight regimes that amplify imbalance; we characterize favorable regions and adapt sampling to remain within them. Our approach, CO3, is plug-and-play, requires no model tuning, and complements standard classifier-free guidance. Experiments on diverse multi-concept prompts indicate improvements in concept coverage, balance and robustness, with fewer dropped or distorted concepts com- pared to standard baselines and prior compositional methods. Results suggest that lightweight corrective guidance can substantially mitigate brittle semantic alignment behavior in modern diffusion systems.

Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discrete tokens with quantization loss. In this paper, we push the autoregressive paradigm forward with NextStep-1, a 14B autoregressive model paired with a 157M flow matching head, training on discrete text tokens and continuous image tokens with next-token prediction objectives. NextStep-1 achieves state-of-the-art performance for autoregressive models in text-to-image generation tasks, exhibiting strong capabilities in high-fidelity image synthesis. Furthermore, our method shows strong performance in image editing, highlighting the power and versatility of our unified approach. To facilitate open research, we will release our code and models to the community.

Automated knowledge graph (KG) construction is essential for navigating the rapidly expanding body of scientific literature. However, existing approaches face persistent challenges: they struggle to recognize long multi-word entities, often fail to generalize across domains, and typically overlook the hierarchical and logically constrained nature of scientific knowledge. While general-purpose large language models (LLMs) offer some adaptability, they are computationally expensive and yield inconsistent accuracy on specialized, domain-heavy tasks such as scientific knowledge graph construction. As a result, current KGs are shallow and inconsistent, limiting their utility for exploration and synthesis. We propose a two-stage framework for scalable, zero-shot scientific KG construction. The first stage, Z-NERD, introduces (i) Orthogonal Semantic Decomposition (OSD), which promotes domain-agnostic entity recognition by isolating semantic “turns” in text, and (ii) a Multi-Scale TCQK attention mechanism that captures coherent multi-word entities through n-gram–aware attention heads. The second stage, HGNet, performs relation extraction with hierarchy-aware message passing, explicitly modeling parent, child, and peer relations. To enforce global consistency, we introduce two complementary objectives: a Differentiable Hierarchy Loss to discourage cycles and shortcut edges, and a Continuum Abstraction Field (CAF) Loss that embeds abstraction levels along a learnable axis in Euclidean space. To the best of our knowledge, this is the first approach to formalize hierarchical abstraction as a continuous property within standard Euclidean embeddings, offering a simpler and more interpretable alternative to hyperbolic methods. To address data scarcity, we also release SPHERE, a large-scale, multi-domain benchmark for hierarchical relation extraction. Our framework establishes a new state of the art on benchmarks such as SciERC, SciER and SPHERE benchmarks, improving named entity recognition (NER) by 8.08\% and relation extraction (RE) by 5.99\% on the official out-of-distrubtion test sets. In zero-shot settings, the gains are even more pronounced, with improvements of 10.76\% for NER and 26.2\% for RE, marking a significant step toward reliable and scalable scientific knowledge graph construction.

Combining Chain-of-Thought (CoT) with Reinforcement Learning (RL) improves text-to-image (T2I) generation, yet the underlying interaction between CoT's exploration and RL's optimization remains unclear. We present a systematic entropy-based analysis that yields three key insights: (1) CoT expands the generative exploration space, while RL contracts it toward high-reward regions; (2) final reward is strongly negatively correlated with both the mean and variance of image-token entropy, highlighting the need to reduce uncertainty and instability; and (3) the entropy of the textual CoT directly governs downstream image quality, with lower-entropy CoTs leading to better generations. Motivated by these findings, we propose Entropy-Guided Group Relative Policy Optimization (EG-GRPO), a fine-tuning strategy that reallocates optimization budget by uncertainty: low-entropy tokens are excluded from reward-driven updates to preserve stability, while high-entropy tokens receive an entropy bonus that encourages structured exploration without collapse. Experiments on standard T2I benchmarks demonstrate that EG-GRPO achieves state-of-the-art performance.

Human mobility generation aims to synthesize plausible trajectory data, which is widely used in urban system research. While Large Language Model-based methods excel at generating routine trajectories, they struggle to capture deviated mobility during large-scale societal events. This limitation stems from two critical gaps: (1) the absence of event-annotated mobility datasets for design and evaluation, and (2) the inability of current frameworks to reconcile competitions between users' habitual patterns and event-imposed constraints when making trajectory decisions. This work addresses these gaps with a twofold contribution. First, we construct the first event-annotated mobility dataset covering three major events: Typhoon Hagibis, COVID-19, and the Tokyo 2021 Olympics. Second, we propose ELLMob, a self-aligned LLM framework that first extracts competing rationales between habitual patterns and event constraints, based on Fuzzy-Trace Theory, and then iteratively aligns them to generate trajectories that are both habitually grounded and event-responsive. Extensive experiments show that ELLMob wins state-of-the-art baselines across all events, demonstrating its effectiveness.

Recent advances in inference-time alignment of diffusion models have shown reduced susceptibility to reward over-optimization. However, when aligning with multiple black-box reward functions, the number of required queries grows exponentially with the number of reward functions, making the alignment process highly inefficient. To address the challenge, we propose the first inference-time soup strategy, named Sample Reward Soups (SRSoup), for Pareto-optimal sampling across the entire space of preferences. Specifically, at each denoising step, we independently steer multiple denoising distributions using reward-guided search gradients (one for each reward function) and then linearly interpolate their search gradients. This design is effective because sample rewards can be shared when two denoising distributions are close, particularly during the early stages of the denoising process. As a result, SRSoup significantly reduces the number of queries required in the early stages without sacrificing performance. Extensive experiments demonstrate the effectiveness of SRSoup in aligning T2I models with diverse reward functions, establishing a practical and scalable solution.